AI Coding Unlimited

AI Coding Unlimited — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  Security awareness

  Security awareness is the knowledge and attitude members of an organization possess regarding the protection of the physical, and especially informational, assets of that organization. However, it is very tricky to implement because organizations are not able to impose such awareness directly on employees as there are no ways to explicitly monitor people's behavior. That being said, the literature does suggest several ways that such security awareness could be improved. Many organizations require formal security awareness training for all workers when they join the organization and periodically thereafter, usually annually. Another main force that is found to have a strong correlation with employees' security awareness is managerial security participation. It also bridges security awareness with other organizational aspects. == Relationship between Security Awareness and Human Factors == Employees' behavior, cognitive biases, and decision-making processes influence the effectiveness of security measures. Research indicates that psychological factors, such as optimism bias, overconfidence, and habitual behaviors, can undermine security awareness initiatives. To address these challenges, organizations are increasingly using behavioral analytics and security nudges—subtle prompts like password reminders and phishing warnings—to encourage secure behavior. Human error remains the leading cause of cybersecurity incidents. A 2023 IBM Security report found that 95% of breaches are due to human mistakes, including falling for phishing emails, using weak passwords, and mishandling sensitive data. Organizations emphasize security awareness training as a key strategy to mitigate this risk. It is particularly important for leadership to foster a culture of cybersecurity and to provide targeted training to increase security awareness among all employees across the organization. == Coverage == Topics covered in security awareness training include: The nature of sensitive material and physical assets they may come in contact with, such as trade secrets, privacy concerns and government classified information Employee and contractor responsibilities in handling sensitive information, including review of employee nondisclosure agreements Requirements for proper handling of sensitive material in physical form, including marking, transmission, storage and destruction Proper methods for protecting sensitive information on computer systems, including password policy and use of two-factor authentication Other computer security concerns, including malware, phishing, social engineering, etc. Workplace security, including building access, wearing of security badges, reporting of Incidents, forbidden articles, etc. Consequences of failure to properly protect information, including potential loss of employment, economic consequences to the firm, damage to individuals whose private records are divulged, and possible civil and criminal penalties Security awareness means understanding that there is the potential for some people to deliberately or accidentally steal, damage, or misuse the data that is stored within a company's computer systems and throughout its organization. Therefore, it would be prudent to support the assets of the institution (information, physical, and personal) by trying to stop that from happening. According to the European Network and Information Security Agency, "Awareness of the risks and available safeguards is the first line of defence for the security of information systems and networks." "The focus of Security Awareness consultancy should be to achieve a long term shift in the attitude of employees towards security, whilst promoting a cultural and behavioural change within an organisation. Security policies should be viewed as key enablers for the organisation, not as a series of rules restricting the efficient working of your business." == Role of Gamification and Interactive Training == Modern security awareness programs increasingly utilize gamification, phishing simulations, and interactive learning modules. Studies have shown that engaging employees through serious games, reward systems, and real-world attack simulations improves retention and application of security practices. One example is phishing simulation training, where employees receive simulated phishing emails to test their ability to recognize threats. Research indicates that repeated exposure to such exercises leads to long-term improvements in security awareness. == Legislation and Compliance Requirements == Many industries mandate security awareness training to comply with regulations such as: General Data Protection Regulation (GDPR) – requires organizations to ensure data protection awareness among employees. Health Insurance Portability and Accountability Act (HIPAA) – mandates security awareness programs for healthcare providers. Payment Card Industry Data Security Standard (PCI-DSS) – enforces security training for businesses handling payment card information. == Measuring security awareness == In a 2016 study, researchers developed a method of measuring security awareness. Specifically they measured "understanding about circumventing security protocols, disrupting the intended functions of systems or collecting valuable information, and not getting caught" (p. 38). The researchers created a method that could distinguish between experts and novices by having people organize different security scenarios into groups. Experts will organize these scenarios based on centralized security themes where novices will organize the scenarios based on superficial themes. Security awareness is also assessed through real-time security metrics, such as tracking phishing click rates, password reuse tendencies, and policy adherence rates. Organizations are adopting continuous monitoring strategies to provide immediate feedback to employees about risky behavior and suggest corrective actions. == Evolving cyber threats and security awareness strategies == As cyber threats continue to evolve, security awareness programs must adapt to new attack vectors, such as AI-driven cyberattacks, deepfakes, and insider threats. ENISA's Threat Landscape report highlights the increasing prominence of these emerging threats, stressing the need for security measures that address both traditional attacks like ransomware and malware, as well as more sophisticated techniques such as Living Off Trusted Sites (LOTS) and advanced evasion methods used by cybercriminals.

  Read more →
• 

  Air Force Network

  Air Force Network (AFNet) is an Indian Air Force (IAF) owned, operated and managed digital information grid. The AFNet replaces the Indian Air Force's (IAF) old communication network set-up using the tropo-scatter technology of the 1950s making it a true net-centric combat force. The IAF project is part of the overall mission to network all three services; The Indian Army, The Indian Navy and The Indian Air Force. The former Defence Minister AK Antony inaugurated the IAF's the AFNET on 14 September 2010 dedicating it to the people of India, for their direct or indirect participation in the communication revolution. == Background == Armed Forces in India has been using troposcatters as primary means of military communications since the 1950s, thereby occupying huge and expensive 2G and 3G spectrums which otherwise could have been used for expanding and de-clogging the civilian wireless communication network. The rapid expansion of civilian mobile telephony leading to need for larger bandwidth for wireless communication and commercial need to operate the 3G network necessitated the Government of India to have the Indian Armed Forces vacate the spectrum occupied by them. Thus the government of India through Department of Telecommunication (DoT) started a project called "Network for Spectrum" to set up a fiber optics network for the exclusive use of Indian Armed Forces in exchange for spectrum being released by the Defence Forces. The aim of 'Network for Spectrum' being twofold - to facilitate the growth of national tele-density on the one hand, and ensuring modernization of defence communications with the state-of-the-art communication infrastructure, and to support net-centric military operations. The Department of Telecom and the Ministry of Defence signed the memorandum of understanding for vacating the spectrum and setting up dedicated network for the use of defence forces. In this MoU, DoT agreed to laying of 40,000 route kilometres of optical fibre cable connecting 219 Army stations, 33 Navy stations and 162 points for the Air Force. It further agreed to setting up an exclusive defence band and Defence Interest Zone along 100 km of the international border, where spectrum will be reserved only for use by the Armed Forces. The total cost of implementing "Network for Spectrum" project is estimated to be ₹ 10,000 crores. AFNet is Indian Air Force component of Digital Information Grid under "Network for Spectrum" project and the AFNet has been extended and connected to the Digital Information Grid Project under implementation for the Indian Navy and the Indian Army on 2015. == Project Origin == The Air Force Network (AFNet) had been developed by the Indian Air Force at a cost of ₹1,077 crore (US$235.53 million) in collaboration with HCL Technologies and Bharat Sanchar Nigam Limited. It will replace the Air Force's more than half-a-century-old telecom network. This project is part of the defence ministry's initiative to digitize the communication systems of the three armed forces under "Network for Spectrum" initiative to improve coordination among themselves and other Military and Strategic Institution. IAF was the first to complete this gigabyte digital information grid implemented under the AFNet project. AFNet will be connected and extended to a Unified Digital Grid encompassing all the legs of Indian Armed Forces. The then defence minister, A. K. Antony, inaugurated the AFNet, IAF's gigabyte digital information grid. The grid is aimed at improving the network-centric warfare capability of the Air Force. The event also saw the presence of other personalities including the then Minister of Communication & IT, A. Raja; the Marshal of the Air Force, Arjan Singh; the Chief of the Air Staff, the Chief of the Army Staff and other officials from the three services and members of the Industry. The event also featured a practice interception of a simulated aerial target by a MiG-29 which took off from an airbase in the Punjab sector using the AFNet capabilities. Further capabilities in line with network centric warfare were also demonstrated. This included sharing information, videos and pictures by operational assets and platforms like UAVs and AWACS to decision-makers who are several hundred kilometres apart. == Technology, Design & Structure == AFNet incorporates the latest traffic transportation technology in form of Internet Protocol (IP) packets over the network using Multiprotocol Label Switching (MPLS). A large Voice over Internet Protocol (VoIP) layer with stringent quality of service enforcement will facilitate robust, high quality voice, video and conferencing solutions. AFNet will prove to be an effective force multiplier for intelligence analysis, mission planning and control, post-mission feedback and related activities like maintenance, logistics and administration. A comprehensive design with multi-layer security precautions for “Defence in Depth” have been planned by incorporating encryption technologies, Intrusion Prevention Systems to ensure the resistance of the IT system against information manipulation and eavesdropping. The network is secured with a host of advanced state-of-the-art encryption technologies. It is designed for high reliability with redundancy built into the network design itself. The AFNet is also capable of transmitting video from unmanned surveillance aircraft (UAV), pictures from airborne warning and control systems (AWACS) to decision makers on the ground and providing intelligence inputs from remote areas. The AFNet is also expected to facilitate accelerated economic growth by providing radio frequency spectrum for telecommunication purposes. AFNET will be the largest Multi-protocol Label Switching (MPLS) network in the defence segment. == Demonstration == At the AFNet launch, the IAF showcased a practice interception of simulated enemy targets by a pair of Mig-29 fighter aircraft airborne from an advanced airbase in the Punjab sector using the gigabyte digital information grid. During the AFNet-assisted operations, the Indian fighter jets neutralised intruding targets in the western sector, which was played out live on the giant screens at the Air Force auditorium offering a glimpse of the harnessed potential of the system. The final orders for engaging the enemy targets were issued live by Antony, whose queries about how the operation went were responded to by the pilot as "excellent". Various other functionalities contributing towards Network Centric Warfare were also showcased. These consisted of facilitating video from Unmanned Aerial Vehicle (UAV), pictures from an AWACS aircraft to the decision-makers on ground sitting hundreds of kilometres away, providing intelligence inputs from far-flung areas at central locations seamlessly. This was possible mainly because of the robust networking platform provided by AFNet. == Integrated Air Command and Control System == Integrated Air Command and Control System (IACCS) is an automated command and control system for air defence operated by the Indian Air Force. IACCS operations rides the AFNET backbone integrating all ground-based and airborne sensors, air defense weapon systems and command and control (C2) nodes. Subsequent integration with other services networks and civil radars will provide an integrated Air Situation Picture to operators to carry out AD role. The project was envisaged in 1995 following the Purulia arms drop case and was a part of IAF’s first Air Power Doctrinal manual issued in the 2000s, later revised in 2022. The first node in the western sectors had been operationalised by September 2010. The first five nodes located in the western and south western sectors were commissioned in 2011. The Air Force was preparing to seek clearance for five further nodes which would cover the rest of the nation including the island territories. Through the IACCS, IAF will connect all of its space, air and ground assets quickly, for total awareness of a region. This will offer connectivity for all the ground platforms and airborne platforms (including AEW&C), as a part of the network centricity of IAF. The IACCS also facilitates real-time transport of images, data and voice, amongst satellites, aircraft and ground stations. By 2018, five IACCS nodes had been established including Barnala (Punjab), Wadsar (Gujarat), Aya Nagar (Delhi), Jodhpur (Rajasthan) and Ambala (Haryana). Following this, under Phase-II, 4 additional nodes and 10 sub-nodes are to be set up. The major nodes will be established in the Eastern, Central, Southern and Andaman and Nicobar sectors. The second phase will cost ₹8,000 crore (equivalent to ₹110 billion or US$1.1 billion in 2023). IACCS successfully integrated all operating radars, including its own, the Army's, and civilian ones, in 2023. This enabled the autonomous firing response capability to take down incoming missiles, aircraft, and UAVs. The Akashteer system of the Indian Army is being integrated with the IACCS

  Read more →
• 

  Viral marketing

  Viral marketing is a business strategy that uses existing social networks to promote a product or service on social media platforms. Its name refers to how consumers spread information about a product with other people, much in the same way that a virus spreads from one person to another. It can be delivered by word of mouth, or enhanced by the network effects of the Internet and mobile networks. The concept is often misused or misunderstood, as people apply it to any successful enough story without taking into account the word "viral". Viral advertising is personal and, while coming from an identified sponsor, it does not mean businesses pay for its distribution. Most of the well-known viral ads circulating online are ads paid by a sponsor company, launched either on their own platform (company web page or social media profile) or on social media websites such as YouTube. Consumers receive the page link from a social media network or copy the entire ad from a website and pass it along through e-mail or posting it on a blog, web page or social media profile. Viral marketing may take the form of video clips, advergames, ebooks, brandable software, images, text messages, email messages, or web pages. The most commonly utilized transmission vehicles for viral messages include pass-along based, incentive based, trendy based, and undercover based. However, the creative nature of viral marketing enables an "endless amount of potential forms and vehicles the messages can utilize for transmission", including mobile devices. The ultimate goal of marketers interested in creating successful viral marketing programs is to create viral messages that appeal to individuals with high social networking potential (SNP) and that have a high probability of being presented and spread by these individuals and their competitors in their communications with others in a short period. The term "viral marketing" has also been used pejoratively to refer to stealth marketing campaigns—marketing strategies that advertise a product to people without them knowing they are being marketed to. == History == The emergence of "viral marketing", as an approach to advertisement, has been tied to the popularization of the notion that ideas spread like viruses. The field that developed around this notion, memetics, peaked in popularity in the 1990s. As this then began to influence marketing gurus, it took on a life of its own in that new context. The brief career of Australian pop singer Marcus Montana is largely remembered as an early example of viral marketing. In early 1989, thousands of posters declaring "Marcus is Coming" were placed around Sydney, generating discussion and interest within the media and the community about the meaning of the mysterious advertisements. The campaign successfully made Montana's musical debut a talking point, but his subsequent music career was a failure. The term is found in PC User magazine in 1989 with a somewhat differing meaning. It was later used by Jeffrey Rayport in the 1996 Fast Company article "The Virus of Marketing", and Tim Draper and Steve Jurvetson of the venture capital firm Draper Fisher Jurvetson in 1997 to describe Hotmail's practice of appending advertising to outgoing mail from their users. Doug Rushkoff, a media critic, wrote about viral marketing on the Internet in 1996. Bob Gerstley wrote about algorithms designed to identify people with high "social networking potential." Gerstley employed SNP algorithms in quantitative marketing research. In 2004, the concept of the alpha user was coined to indicate that it had now become possible to identify the focal members of any viral campaign, the "hubs" who were most influential. Alpha users could be targeted for advertising purposes most accurately in mobile phone networks, due to their personal nature. In early 2013, the first ever Viral Summit was held in Las Vegas. == Factors == Marketer Jonah Berger defines six key factors that drive virality, organized in an acronym called STEPPS: Social currency – the better something makes people look, the more likely they will be to share it Triggers – things that are "top of mind" are more likely to be "tip of the tongue" Emotion – when people care, they share Public – the easier something is to see, the more likely people are to imitate it Practical value – people share useful information to help others Stories – like a Trojan Horse, stories carry messages and ideas along for the ride. Another important factor that drives virality is the propagativity of the content, referring to the ease with which consumers can redistribute it. == Psychology == To form deeper connections with viewers and increase the chances of virality, many marketers use psychological principles. They argue that this approach is scientific and can foster an environment where the odds of gaining traction are much higher. People find psychological safety and can develop a sense of trust when more people interact with online content. For this reason, marketers work to develop media that resonates with viewers on a deeper, emotional level as this approach frequently results in higher engagement. This level of interaction serves as a sign of approval, reducing the personal risk that is subconsciously linked to associating oneself with a company or brand’s content. Professor Jonah Berger at the University of Pennsylvania's Wharton School of Business affirms that marketing campaigns that trigger psychological responses linked to strong emotions tend to perform better. In particular, Berger found that positive emotions like happiness, joy, and excitement have more successful share rates than their negative counterparts. This outcome results from the human instinct to respond more positively to content with activating emotions, increasing the desire to share content, which contributes to its virality. Viral marketing utilizes the primitive feeling of frisson to increase their view and share counts. This feeling of excitement is considered powerful because of its ability to cause a physical response. From increased heart rates to full body chills, Professor Brent Coker at the University of Melbourne describes that this approach to marketing triggers a primitive response that immerses the viewer in the content on a deeper level. Researchers Juliana Fernandes from the University of Florida and Sigal Segev from the Florida International University also found that people are more inclined to share emotional campaigns over those that are heavily informational. They claim that consumers do not often care to learn about a product’s actual features and benefits. Instead, people prefer to be immersed in experience-based content that creates an emotional impact. Companies and brands can benefit from treating their content in this manner and go viral more frequently than those who do not. Social proof is another psychological phenomenon that impacts viral content. Experts in this field argue that it is a natural instinct to want to behave similarly to others because it results in positive validation. This phenomenon explains the human need to conform, so marketers focus on creating engaging content that encourages interactions and causes a snowball effect. This subconsciously influences people to like, comment, and share if they already see others doing the same. Social proof goes further by providing people with a form of social currency. When individuals interact with and share content, they become associated with the topics at hand. People naturally tend to perceive one another, and this pattern carries over to the digital world. As a result, many people tend to be vigilant about the viral marketing they engage with, since they want to be perceived positively. Companies and brands have the opportunity to develop social currency themselves by aligning with their target audiences and creating marketing campaigns that fit their interests or match their values. == Methods and metrics == According to marketing professors Andreas Kaplan and Michael Haenlein, to make viral marketing work, three basic criteria must be met, i.e., giving the right message to the right messengers in the right environment: Messenger: Three specific types of messengers are required to ensure the transformation of an ordinary message into a viral one: market mavens, social hubs, and salespeople. Market mavens are individuals who are continuously 'on the pulse' of things (information specialists); they are usually among the first to get exposed to the message and who transmit it to their immediate social network. Social hubs are people with an exceptionally large number of social connections; they often know hundreds of different people and have the ability to serve as connectors or bridges between different subcultures. Salespeople might be needed who receive the message from the market maven, amplify it by making it more relevant and persuasive, and then transmit it to the social hub for further distr

  Read more →
• 

  Social media as a news source

  Social media as a news source is defined as the use of online social media platforms such as Instagram, TikTok, and Facebook rather than the use of traditional media platforms like the newspaper or live TV to obtain news. Television had just begun to turn a nation of people who once listened to media content into watchers of media content between the 1950s and the 1980s when the popularity of social media had also begun creating a nation of media content creators. Almost half of Americans use social media as a news source, according to the Pew Research Center. As social media's role in news consumption grows, questions have emerged about its impact on knowledge, the formation of echo chambers, and the effectiveness of fact-checking efforts in combating misinformation. Social media platforms allow user-generated content and sharing content within one's own virtual network. Using social media as a news source allows users to engage with news in a variety of ways including: Consuming and discovering news Sharing or reposting news Posting one's own photos, videos, or reports of news (i.e., engage in citizen or participatory journalism) Commenting on news posts Using social media as a news source has become an increasingly popular way for people of all age groups to obtain current and important information. Just like many other new forms of technology there are going to be pros and cons. There are ways that social media positively affects the world of news and journalism but it is important to acknowledge that there are also ways in which social media has a negative effect on the news. With this accessibility, people now have more ways to consume false news, biased news, and even disturbing content. In 2019, the Pew Research Center created a poll that reported Americans are wary about the ways that social media sites share news and certain content. This wariness of accuracy grew as awareness that social media sites could be exploited by bad actors who concoct false narratives and fake news. == Relationship to traditional news sources == Unlike traditional news platforms such as newspapers and news shows, social media platforms allow people without professional journalistic backgrounds to create news and cover events that news agencies might not cover. Social media users may read a set of news that differs slightly from what newspaper editors prioritize in the print press. A 2019 study found that Facebook and Twitter users are more likely to share politics, public affairs, and visual media news. Typically social media users circulate more towards posting about negative news. A study of tweets found that while optimistic-sounding and neutral-sounding tweets were equally likely to express certainty or uncertainty, the pessimistic tweets were nearly twice as likely to appear certain of an outcome than uncertain. These results could imply that posts of a more pessimistic nature that are also written with an air of certainty are more likely to be shared or otherwise permeate groups on Twitter. A similar bias towards negativity has developed on Facebook, where internal memos revealed that an algorithm built to promote "meaningful social interaction" actually incentivized publishers to promote negative and sensational news. Biases towards negativity need to be considered when the utility of new media is addressed, as the potential for human opinion to overemphasize any particular news story is greater despite general improvement. In order to compete in this rapidly changing technological environment, there has been an upheaval of traditional news sources onto online spaces. The production and circulation of newspaper prints have continued to globally decline in accordance with the increasing presence of news outlets on social media. Prominent platforms such as Twitter and Facebook have been key in engaging users through the integration of journalistic news into their newsfeeds. This feature has now become a foundational part of these apps' interfaces. Social media incentivizes both legacy news brands and individual professional journalists to share their reporting and interact with audiences on social platforms to boost engagement. However, most people who consume news on social media report that accessing news is not their main motivation for being on social media, but rather, they see and consume news incidentally. Nonetheless, informational interviews reveal that these consumers rely on being informed through social media. Some news consumers attest that a news brand's participation in social media does not improve their trust in the brand and that more in-depth reporting and more transparency about biases would improve trust instead. == Use as a news source == Globally, data from 2020 shows that over 70% of adult participants from Kenya, South Africa, Chile, Bulgaria, Greece, and Argentina utilized social media for news while those from France, the UK, the Netherlands, Germany, and Japan were reportedly less than 40 percent. According to the Pew Research Center, 20% of adults in the United States in 2018 said they get their news from social media "often," compared to 16% who said they often get news from print newspapers, 26% who often get it from the radio, 33% who often get it from news websites, and 49% who often get it from TV. The same survey found that social media was the most popular way for American adults age 18–29 to get news, the second-to-last most popular way for Americans age 20–49 to get news, and the least popular way for American adults age 50-64 and 65+ to get the news. In 2019, the Pew Research Center found that over half of Americans (54%) either got their news "sometimes" or "often" from social media, and Facebook was the most popular social media site where American adults got their news. However, at least 50% off all respondents reported that the following were either a "very big problem" or a "moderately big problem" for getting news on social media: One-sided news (83%) Inaccurate news (81%) Censorship of the news (69%) Uncivil discussions about the news (69%) Harassment of journalists (57%) News organizations or personalities being banned (53%) Violent or disturbing news images or videos (51%) In a later survey from the same year, the Pew Research Center reported that 18% of American adults reported that the most common way they get news about politics and the election was from social media. Additional source information shows that from politics and the United States presidential election in 2016, the popularity of fake news had grown to global attention. With this information, the study explains that more than 60 percent of adults receive their news from social media, the most popular being Facebook. With the increase of fake news, and the large amount of adult participation on these social media sites, it made it much harder for those who were searching for news to find a source that they could find credible. Another study found that adult participants found their own friends on Facebook to be a more reliable source of information online compared to a professional news organization. Although, when news was posted by a news organization online, they were then found more reliable compared to when they are shared by their online friends. Showing that adult participants found that the news that was only posted on Facebook and social media was much more credible to them than compared to other forms of information spreading. The study further states that these outcomes have the potential explanation that the topic of the news article played a part in the ways they were affected. This could have affected the way adult participants interacted with the different news sources, such as their online friends compared to a news organization, prominently because depending on the story, they want to have the correct information about the news from the most credible source. === By young people === Social media platforms are some of the most easily accessible forms of news and with the growing generations, the technology is only going to grow. With that, the use of social media in younger generations is also going to grow alongside it. Technology in the hands of young kids can be a concern moving into the future. Globally, there is evidence that through social media, youth have become more directly involved in protests, social campaigns and generally, in the sharing of news across multiple platforms. The number of people who use social media platforms such as Twitter, Facebook, Instagram, or Snapchat as ways to seek information has increased significantly in recent years especially for people who are part of the younger generation.TikTok is a rapidly expanding platform that young adults can use to find news content on social media. TikTok is one of the sites that young adults and teens utilize to get news about trending themes and controversial topics. The younger generation accepts without hesitation the information that thei

  Read more →
• 

  Uniform convergence in probability

  Uniform convergence in probability is a form of convergence in probability in statistical asymptotic theory and probability theory. It means that, under certain conditions, the empirical frequencies of all events in a certain event-family uniformly converge to their theoretical probabilities. Uniform convergence in probability has applications to statistics as well as machine learning as part of statistical learning theory. Specifically, the Glivenko-Cantelli theorem and the homonymous classes of functions are fundamentally related to uniform convergence. The law of large numbers says that, for each single event A {\displaystyle A} , its empirical frequency in a sequence of independent trials converges (with high probability) to its theoretical probability. In many application however, the need arises to judge simultaneously the probabilities of events of an entire class S {\displaystyle S} from one and the same sample. Moreover, it, is required that the relative frequency of the events converge to the probability uniformly over the entire class of events S {\displaystyle S} . The Uniform Convergence Theorem gives a sufficient condition for this convergence to hold. Roughly, if the event-family is sufficiently simple (its VC dimension is sufficiently small) then uniform convergence holds. == Definitions == For a class of predicates H {\displaystyle H} defined on a set X {\displaystyle X} and a set of samples x = ( x 1 , x 2 , … , x m ) {\displaystyle x=(x_{1},x_{2},\dots ,x_{m})} , where x i ∈ X {\displaystyle x_{i}\in X} , the empirical frequency of h ∈ H {\displaystyle h\in H} on x {\displaystyle x} is Q ^ x ( h ) = 1 m | { i : 1 ≤ i ≤ m , h ( x i ) = 1 } | . {\displaystyle {\widehat {Q}}_{x}(h)={\frac {1}{m}}|\{i:1\leq i\leq m,h(x_{i})=1\}|.} The theoretical probability of h ∈ H {\displaystyle h\in H} is defined as Q P ( h ) = P { y ∈ X : h ( y ) = 1 } . {\displaystyle Q_{P}(h)=P\{y\in X:h(y)=1\}.} The Uniform Convergence Theorem states, roughly, that if H {\displaystyle H} is "simple" and we draw samples independently (with replacement) from X {\displaystyle X} according to any distribution P {\displaystyle P} , then with high probability, the empirical frequency will be close to its expected value, which is the theoretical probability. Here "simple" means that the Vapnik–Chervonenkis dimension of the class H {\displaystyle H} is small relative to the size of the sample. In other words, a sufficiently simple collection of functions behaves roughly the same on a small random sample as it does on the distribution as a whole. The Uniform Convergence Theorem was first proved by Vapnik and Chervonenkis using the concept of growth function. == Uniform Convergence Theorem == The statement of the Uniform Convergence Theorem is as follows: If H {\displaystyle H} is a set of { 0 , 1 } {\displaystyle \{0,1\}} -valued functions defined on a set X {\displaystyle X} and P {\displaystyle P} is a probability distribution on X {\displaystyle X} then for ε > 0 {\displaystyle \varepsilon >0} and m {\displaystyle m} a positive integer, we have: P m { | Q P ( h ) − Q x ^ ( h ) | ≥ ε for some h ∈ H } ≤ 4 Π H ( 2 m ) e − ε 2 m / 8 . {\displaystyle P^{m}\{|Q_{P}(h)-{\widehat {Q_{x}}}(h)|\geq \varepsilon {\text{ for some }}h\in H\}\leq 4\Pi _{H}(2m)e^{-\varepsilon ^{2}m/8}.} In the above, for any x ∈ X m , {\displaystyle x\in X^{m},} Q P ( h ) = P { ( y ∈ X : h ( y ) = 1 } , {\displaystyle Q_{P}(h)=P\{(y\in X:h(y)=1\},} Q ^ x ( h ) = 1 m | { i : 1 ≤ i ≤ m , h ( x i ) = 1 } | {\displaystyle {\widehat {Q}}_{x}(h)={\frac {1}{m}}|\{i:1\leq i\leq m,h(x_{i})=1\}|} and | x | = m . {\displaystyle |x|=m.} P m {\displaystyle P^{m}} indicates that the probability is taken over x {\displaystyle x} consisting of m {\displaystyle m} i.i.d. draws from the distribution P . {\displaystyle P.} Finally, the growth function Π H {\displaystyle \Pi _{H}} is defined in the following way, for any { 0 , 1 } {\displaystyle \{0,1\}} -valued functions H {\displaystyle H} over X {\displaystyle X} and for any natural number m {\displaystyle m} : Π H ( m ) = max | { h ∩ D : D ⊆ X , | D | = m , h ∈ H } | . {\displaystyle \Pi _{H}(m)=\max |\{h\cap D:D\subseteq X,|D|=m,h\in H\}|.} From the point of view of Learning Theory one can consider H {\displaystyle H} to be the Concept/Hypothesis class defined over the instance set X {\displaystyle X} . Crucially, the Sauer–Shelah lemma implies that Π H ( m ) ≤ m d {\displaystyle \Pi _{H}(m)\leq m^{d}} , where d {\displaystyle d} is the VC dimension of H {\displaystyle H} . == Proof of the Uniform Convergence Theorem == and are the sources of the proof below. Before we get into the details of the proof of the Uniform Convergence Theorem we will present a high level overview of the proof. Symmetrization: We transform the problem of analyzing | Q P ( h ) − Q ^ x ( h ) | ≥ ε {\displaystyle |Q_{P}(h)-{\widehat {Q}}_{x}(h)|\geq \varepsilon } into the problem of analyzing | Q ^ r ( h ) − Q ^ s ( h ) | ≥ ε / 2 {\displaystyle |{\widehat {Q}}_{r}(h)-{\widehat {Q}}_{s}(h)|\geq \varepsilon /2} , where r {\displaystyle r} and s {\displaystyle s} are i.i.d samples of size m {\displaystyle m} drawn according to the distribution P {\displaystyle P} . One can view r {\displaystyle r} as the original randomly drawn sample of length m {\displaystyle m} , while s {\displaystyle s} may be thought as the testing sample which is used to estimate Q P ( h ) {\displaystyle Q_{P}(h)} . Permutation: Since r {\displaystyle r} and s {\displaystyle s} are picked identically and independently, so swapping elements between them will not change the probability distribution on r {\displaystyle r} and s {\displaystyle s} . So, we will try to bound the probability of | Q ^ r ( h ) − Q ^ s ( h ) | ≥ ε / 2 {\displaystyle |{\widehat {Q}}_{r}(h)-{\widehat {Q}}_{s}(h)|\geq \varepsilon /2} for some h ∈ H {\displaystyle h\in H} by considering the effect of a specific collection of permutations of the joint sample x = r | | s {\displaystyle x=r||s} . Specifically, we consider permutations σ ( x ) {\displaystyle \sigma (x)} which swap x i {\displaystyle x_{i}} and x m + i {\displaystyle x_{m+i}} in some subset of 1 , 2 , . . . , m {\displaystyle {1,2,...,m}} . The symbol r | | s {\displaystyle r||s} means the concatenation of r {\displaystyle r} and s {\displaystyle s} . Reduction to a finite class: We can now restrict the function class H {\displaystyle H} to a fixed joint sample and hence, if H {\displaystyle H} has finite VC Dimension, it reduces to the problem to one involving a finite function class. We present the technical details of the proof. It should be stressed that this proof glosses over details like the measurability of the events V {\displaystyle V} and R {\displaystyle R} ; measurability is granted in the case of H {\displaystyle H} being finite or countable, but this is not normally the case in standard applications of the theorem (e.g. for statistical learning theory or to prove the Glivenko-Cantelli theorem). To get measurability, one needs to use a notion of separability of the underlying space, possibly related to H {\displaystyle H} . === Symmetrization === Lemma: Let V = { x ∈ X m : | Q P ( h ) − Q ^ x ( h ) | ≥ ε for some h ∈ H } {\displaystyle V=\{x\in X^{m}:|Q_{P}(h)-{\widehat {Q}}_{x}(h)|\geq \varepsilon {\text{ for some }}h\in H\}} and R = { ( r , s ) ∈ X m × X m : | Q r ^ ( h ) − Q ^ s ( h ) | ≥ ε / 2 for some h ∈ H } . {\displaystyle R=\{(r,s)\in X^{m}\times X^{m}:|{\widehat {Q_{r}}}(h)-{\widehat {Q}}_{s}(h)|\geq \varepsilon /2{\text{ for some }}h\in H\}.} Then for m ≥ 2 ε 2 {\displaystyle m\geq {\frac {2}{\varepsilon ^{2}}}} , P m ( V ) ≤ 2 P 2 m ( R ) {\displaystyle P^{m}(V)\leq 2P^{2m}(R)} . Proof: By the triangle inequality, if | Q P ( h ) − Q ^ r ( h ) | ≥ ε {\displaystyle |Q_{P}(h)-{\widehat {Q}}_{r}(h)|\geq \varepsilon } and | Q P ( h ) − Q ^ s ( h ) | ≤ ε / 2 {\displaystyle |Q_{P}(h)-{\widehat {Q}}_{s}(h)|\leq \varepsilon /2} then | Q ^ r ( h ) − Q ^ s ( h ) | ≥ ε / 2 {\displaystyle |{\widehat {Q}}_{r}(h)-{\widehat {Q}}_{s}(h)|\geq \varepsilon /2} . Therefore, P 2 m ( R ) ≥ P 2 m { ∃ h ∈ H , | Q P ( h ) − Q ^ r ( h ) | ≥ ε and | Q P ( h ) − Q ^ s ( h ) | ≤ ε / 2 } = ∫ V P m { s : ∃ h ∈ H , | Q P ( h ) − Q ^ r ( h ) | ≥ ε and | Q P ( h ) − Q ^ s ( h ) | ≤ ε / 2 } d P m ( r ) = A {\displaystyle {\begin{aligned}&P^{2m}(R)\\[5pt]\geq {}&P^{2m}\{\exists h\in H,|Q_{P}(h)-{\widehat {Q}}_{r}(h)|\geq \varepsilon {\text{ and }}|Q_{P}(h)-{\widehat {Q}}_{s}(h)|\leq \varepsilon /2\}\\[5pt]={}&\int _{V}P^{m}\{s:\exists h\in H,|Q_{P}(h)-{\widehat {Q}}_{r}(h)|\geq \varepsilon {\text{ and }}|Q_{P}(h)-{\widehat {Q}}_{s}(h)|\leq \varepsilon /2\}\,dP^{m}(r)\\[5pt]={}&A\end{aligned}}} since r {\displaystyle r} and s {\displaystyle s} are independent. Now for r ∈ V {\displaystyle r\in V} fix an h ∈ H {\displaystyle h\in H} such that | Q P ( h ) − Q ^ r ( h ) | ≥ ε {\displaystyle |Q_{P}(h)-{\widehat {Q}}_{r}(h)|\geq \varepsilon } . For this h {\displaystyle h} , we shall

  Read more →
• 

  Data monetization

  Data monetization, a form of monetization, may refer to the act of generating measurable economic benefits from available data sources (analytics). Less commonly, it may also refer to the act of monetizing data services. In the case of analytics, typically, these benefits accrue as revenue or expense savings, but may also include market share or corporate market value gains. Data monetization leverages data generated through business operations, available exogenous data or content, as well as data associated with individual actors such as that collected via electronic devices and sensors participating in the internet of things. For example, the ubiquity of the internet of things is generating location data and other data from sensors and mobile devices at an ever-increasing rate. When this data is collated against traditional databases, the value and utility of both sources of data increases, leading to tremendous potential to mine data for social good, research and discovery, and achievement of business objectives. Closely associated with data monetization are the emerging data as a service models for transactions involving data by the data item. There are three ethical and regulatory vectors involved in data monetization due to the sometimes conflicting interests of actors involved in the digital supply chain. The individual data creator who generates files and records through his own efforts or owns a device such as a sensor or a mobile phone that generates data has a claim to ownership of data. The business entity that generates data in the course of its operations, such as its transactions with financial institutions or risk factors discovered through feedback from customers also has a claim on data captured through their systems and platforms. However, the person that contributed the data may also have a legitimate claim on the data. Internet platforms and service providers, such as Google or Facebook that require a user to forgo some ownership interest in their data in exchange for use of the platform also have a legitimate claim on the data. Thus the practice of data monetization, although common since 2000, is now getting increasing attention from regulators. The European Union and the United States Congress have begun to address these issues. For instance, in the financial services industry, regulations involving data are included in the Gramm–Leach–Bliley Act and Dodd-Frank. Some individual creators of data are shifting to using personal data vaults and implementing vendor relationship management concepts as a reflection of an increasing resistance to their data being federated or aggregated and resold without compensation. Groups such as the Personal Data Ecosystem Consortium, Patient privacy rights, and others are also challenging corporate cooptation of data without compensation. Financial services companies are a relatively good example of an industry focused on generating revenue by leveraging data. Credit card issuers and retail banks use customer transaction data to improve targeting of cross-sell offers. Partners are increasingly promoting merchant based reward programs which leverage a bank’s data and provide discounts to customers at the same time. == Types of data monetization == Internal data monetization - An organization's data is used internally, resulting in economic benefit. This is commonly the case in organizations using analytics to uncover insights, resulting in improved profit, cost savings or the avoidance of risk. Internal data monetization is currently the most common form of monetization, requiring far fewer security, intellectual property, and legal precautions when compared to other types. The potential economic gains from this type of data monetization are limited by the organization's internal structure and situation. External data monetization - A person or organization makes data they possess available on a for-fee basis to external parties, or as a broker for same. This type of monetization is less common and requires various methods to distribute the data to potential buyers and consumers. However, the economic gain that results from collecting data, packaging and distributing it, can be quite large. == Steps == Identification of available data sources – this includes data currently available for monetization as well as other external data sources that may enhance the value of what’s currently available. Connect, aggregate, attribute, validate, authenticate, and exchange data - this allows data to be converted directly into actionable or revenue generating insight or services. Set terms and prices and facilitate data trading - methods for data vetting, storage, and access. For example, many global corporations have locked and siloed data storage infrastructures, which hinders efficient access to data and cooperative and real-time exchange. Perform Research and analytics – draw predictive insights from existing data as a basis for using data for to reduce risk, enhance product development or performance, or improve customer experience or business outcomes. Action and leveraging – the last phase of monetizing data includes determining alternative or improved data centric products, ideas, or services. Examples may include real-time actionable triggered notifications or enhanced channels such as web or mobile response mechanisms. == Pricing variables and factors == A fee for use of a platform to connect buyers and sellers use of a platform to configure, organize, and otherwise process data included in a data trade connecting or including a device or sensor into a data supply chain connecting and credentialing a creator of a data source and a data buyer – often through a federated identity connecting a data source to other data sources to be included in a data supply chain use of an internet service or other transmission services for uploading and downloading data – sometimes, for an individual, through a personal cloud use of encrypted keys to achieve secure data transfer use of a search algorithm specifically designed to tag data sources that contain data points of value to the data buyer linking a data creator or generator to a data collection protocol or form server actions – such as a notification – triggered by an update to a data item or data source included in a data supply chain A price or exchange or other trade value assigned by a data creator or generator to a data item or a data source offered by a data buyer to a data creator assigned by a data buyer for a data item or a data source formatted according to criteria set by a data buyer An incremental fee assigned by a data buyer for a data item or a data set scaled to the reputation of the data creator == Benefits == Improved decision-making that leads to real time crowd sourced research, improved profits, decreased costs, reduced risk and improved compliance More impactful decisions (e.g., make real-time decisions) More timely (lower latency) decisions (e.g., a vendor making purchase recommendations while the customer is still on the phone or in the store, a customer connecting with multiple vendors to discover the best price, triggered notifications when thresholds are reached for data values) More granular decisions (e.g., localized pricing decisions at an individual or device or sensor level versus larger aggregates). Targeted Marketing (e.g., Vendors with access to big data can make targeted advertisements to specific customers within a set data pool decreasing costs for the advertiser and reaching most interested customers) == Frameworks == There are a wide variety of industries, firms and business models related to data monetization. The following frameworks have been offered to help understand the types of business models that are used: Roger Ehrenberg of IA Ventures, a venture capital firm that invests in this sector, has defined three basic types of data product firms: Contributory databases. The magic of these businesses is that a customer provides their own data in exchange for receiving a more robust set of aggregated data back that provides insight into the broader marketplace, or provides a vehicle for expressing a view. Give a little, get a lot back in return – a pretty compelling value proposition, and one that frequently results in a payment from the data contributor in exchange for receiving enriched, aggregated data. Once these contributory databases are developed and customers become reliant on their insights, they become extremely valuable and persistent data assets. Data processing platforms. These businesses create barriers through a combination of complex data architectures, proprietary algorithms, and rich analytics to help customers consume data in whatever form they please. Often these businesses have special relationships with key data providers, that when combined with other data and processed as a whole create valuable differentiation and competitive barriers. Bloomberg is an example of a powerful

  Read more →
• 

  Strong secrecy

  Strong secrecy is a term used in formal proof-based cryptography for making propositions about the security of cryptographic protocols. It is a stronger notion of security than syntactic (or weak) secrecy. Strong secrecy is related with the concept of semantic security or indistinguishability used in the computational proof-based approach. Bruno Blanchet provides the following definition for strong secrecy: Strong secrecy means that an adversary cannot see any difference when the value of the secret changes For example, if a process encrypts a message m an attacker can differentiate between different messages, since their ciphertexts will be different. Thus m is not a strong secret. If however, probabilistic encryption were used, m would be a strong secret. The randomness incorporated into the encryption algorithm will yield different ciphertexts for the same value of m.

  Read more →
• 

  BitFunnel

  BitFunnel is the search engine indexing algorithm and a set of components used in the Bing search engine, which were made open source in 2016. BitFunnel uses bit-sliced signatures instead of an inverted index in an attempt to reduce operations cost. == History == Progress on the implementation of BitFunnel was made public in early 2016, with the expectation that there would be a usable implementation later that year. In September 2016, the source code was made available via GitHub. A paper discussing the BitFunnel algorithm and implementation was released as through the Special Interest Group on Information Retrieval of the Association for Computing Machinery in 2017 and won the Best Paper Award. == Components == BitFunnel consists of three major components: BitFunnel – the text search/retrieval system itself WorkBench – a tool for preparing text for use in BitFunnel NativeJIT – a software component that takes expressions that use C data structures and transforms them into highly optimized assembly code == Algorithm == === Initial problem and solution overview === The BitFunnel paper describes the "matching problem", which occurs when an algorithm must identify documents through the usage of keywords. The goal of the problem is to identify a set of matches given a corpus to search and a query of keyword terms to match against. This problem is commonly solved through inverted indexes, where each searchable item is maintained with a map of keywords. In contrast, BitFunnel represents each searchable item through a signature. A signature is a sequence of bits which describe a Bloom filter of the searchable terms in a given searchable item. The bloom filter is constructed through hashing through several bit positions. === Theoretical implementation of bit-string signatures === The signature of a document (D) can be described as the logical-or of its term signatures: S D → = ⋃ t ∈ D S t → {\displaystyle {\overrightarrow {S_{D}}}=\bigcup _{t\in D}{\overrightarrow {S_{t}}}} Similarly, a query for a document (Q) can be defined as a union: S Q → = ⋃ t ∈ Q S t → {\displaystyle {\overrightarrow {S_{Q}}}=\bigcup _{t\in Q}{\overrightarrow {S_{t}}}} Additionally, a document D is a member of the set M' when the following condition is satisfied: S Q → ∩ S D → = S Q → {\displaystyle {\overrightarrow {S_{Q}}}\cap {\overrightarrow {S_{D}}}={\overrightarrow {S_{Q}}}} This knowledge is then combined to produce a formula where M' is identified by documents which match the query signature: M ′ = { D ∈ C ∣ S Q → ∩ S D → = S Q → } {\displaystyle M'=\left\{D\in C\mid {\overrightarrow {S_{Q}}}\cap {\overrightarrow {S_{D}}}={\overrightarrow {S_{Q}}}\right\}} These steps and their proofs are discussed in the 2017 paper. === Pseudocode for bit-string signatures === This algorithm is described in the 2017 paper. M ′ = ∅ foreach D ∈ C do if S D → ∩ S Q → = S Q → then M ′ = M ′ ∪ { D } endif endfor {\displaystyle {\begin{array}{l}M'=\emptyset \\{\texttt {foreach}}\ D\in C\ {\texttt {do}}\\\qquad {\texttt {if}}\ {\overrightarrow {S_{D}}}\cap {\overrightarrow {S_{Q}}}={\overrightarrow {S_{Q}}}\ {\texttt {then}}\\\qquad \qquad M'=M'\cup \{D\}\\\qquad {\texttt {endif}}\\{\texttt {endfor}}\end{array}}}

  Read more →
• 

  24SevenOffice

  24SevenOffice is a Norwegian software company headquartered in Oslo, Norway, with offices in Stockholm, Sweden and London, United Kingdom. Founded in 1997, the company specializes in web-based (SaaS) ERP and CRM systems. == Company history == 24SevenOffice was founded in 1997 in Porsgrunn, Norway, as IKT Interactive AS and marketed as kontorplassen.no. The name "24SevenOffice" was introduced for the company's London branch when the company entered the British market in 2003. The company changed its name to 24SevenOffice in February 2005. Originally based in Skien, the company later moved to Oslo Innovation Center, then to Tjuvholmen in the waterfront Fjord City of Oslo, and now the headquarters are located in Inkognitogaten 33, Solli plass, Oslo. The idea for the company's product was developed in 1996, and 24SevenOffice was an early innovator in the Scandinavian market in web-based enterprise resource planning solutions (ERP). A British office was established at Surrey Business Park in May 2003, with the company launching its web-based (SaaS) utility computing system to the UK SME market in 2004. An office in Chennai, India, was established in 2005, and 24SevenOffice entered the Swedish market when they acquired the leading competitor and ERP-provider Start & Run in a cash deal. In August 2005, the company had an initial public offering that raised NOK 15 million, and the company entered The Norwegian Over the Counter Market list as of 5 October 2005 (the ticker was 24SO), reaching a market value of NOK 175 million, with 5000 customers in Norway. In 2006, the company signed a deal to sponsor rally driver Petter Solberg, at the time the largest private sponsorship in Norwegian sport. Instead of receiving NOK 5 million in cash, Solberg received a 2.9 per cent ownership in the company. The company entered the German-speaking market in April 2006 when an office in Frankfurt am Main was opened. In late August/early September, they established an office with ten sales agents plus a general manager in Stockholm for the Swedish market. 24SevenOffice initiated strategic cooperation with Active 24 in early 2006 to develop a common platform. During the summer, Active 24 was bought by 24SevenOffice's ERP/CRM competitor Mamut (company), and 24SevenOffice terminated the contract with Active 24 in October demanding NOK 200 million in compensation for lost revenue. After a breakdown of settlement negotiations in the Forliksråd in January 2007, 24SevenOffice filed a case against Active 24 for breach of agreement in the Oslo District Court in March. 24SevenOffice lost on all counts in the District Court in December 2007. In January 2008, 24SevenOffice appealed the case to the Borgarting Court of Appeal, reducing the cause of action from NOK 250 to 30 million. 24SevenOffice lost on all counts in the Court of Appeal in December 2008, and was ordered to cover the costs incurred by Active 24 in connection with the dispute totaling NOK 6.91 million. 24SevenOffice appealed the case to the Supreme Court of Norway, but the Supreme Court Appeals Committee in March 2008 unanimously rejected the appeal from 24SevenOffice over the Borgarting Appeal Court's unanimous judgment of December 2008. On a counterclaim from Active 24 and Mamut against 24SevenOffice, the Oslo District Court in May 2010 found, that 24SevenOffice should pay Active 24 NOK 12 million in compensation for wrongfully having terminated the agreement, and a further NOK 360.000 of the opponent's legal costs. 24SevenOffice disagreed with the court ruling, and appealed once again. The Borgarting Court of Appeal in November 2011, ruled to reduce the amount of damages to NOK 4.4 million plus NOK 900.000 in penal interest. With several scrip issues, 24SevenOffice raised 25 million NOK (about $4 million at the time) between October 2005 and July 2006. They entered into a strategic partnership with Bluegarden, who for 30 years had delivered digital services for payroll, human resource planning, recruitment and training, in March 2006, and they made a large-scale agreement in April 2006, with US telecommunications software company Webex, a competitor to Norwegian Tandberg videoconferencing equipment manufacturer. In September 2006, 24SevenOffice signed an agreement with Fokus Bank to provide their customers with extended functionality in Internet banking. 24SevenOffice had by 2007 reportedly 9000 customers, joined the OpenAjax Alliance, and entered into a strategic partnership with Dun & Bradstreet in May 2007, but despite getting listed on Oslo Axess on 22 June (ticker: TFSO), reaching a market capitalization of NOK 120 million, the company was still losing money. The company ended 2007 with a revenue of NOK 21.7 million. In 2008, 24SevenOffice bought 50% of the stocks in telecommunication company Oyatel, partnered with Nets Group to facilitate invoicing for businesses, and telecommunications company Telipol chose 24SevenOffice's second-generation Internet platform for its 8,000 users. They announced an increase in revenues in Q2 to 11.1 million, up from 4.7 million in the same period the year before. 24SevenOffice had a turnover of NOK 37 million in the first half of 2009, a doubling compared to the same period the previous year, and presented its first positive EBITDA in Q2. The Norwegian Association of Auditors signed an agreement with 24SevenOffice in 2011, whereby they only recommend 24SevenOffice as a system for their members to use. On 27 June 2013, the shareholders of 24SevenOffice took off from the stock exchange and privatized the company. In recent years, the company has invested heavily in finance and accounting – and got leading auditing companies such as PwC and KPMG on the customer list. == Products == 24SevenOffice is a web-based (SaaS) ERP system. It includes modules for CRM, accounting, invoicing, e-mail, file/document management and project management. == Awards == 24SevenOffice won the Seal of Excellence in Multimedia Award at the 2004 CeBIT, became Norwegian Gazelle Company of the year 2004, chosen by Dagens Næringsliv and Dun & Bradstreet, won Product of the Year in the Norwegian finance magazine Kapital, and the IKT Grenland Innovation Award in 2008.

  Read more →
• 

  Scalable Coherent Interface

  The Scalable Coherent Interface or Scalable Coherent Interconnect (SCI), is a high-speed interconnect standard for shared memory multiprocessing and message passing. The goal was to scale well, provide system-wide memory coherence and a simple interface; i.e. a standard to replace existing buses in multiprocessor systems with one with no inherent scalability and performance limitations. The IEEE Std 1596-1992, IEEE Standard for Scalable Coherent Interface (SCI) was approved by the IEEE standards board on March 19, 1992. It saw some use during the 1990s, but never became widely used and has been replaced by other systems from the early 2000s. == History == Soon after the Fastbus (IEEE 960) follow-on Futurebus (IEEE 896) project in 1987, some engineers predicted it would already be too slow for the high performance computing marketplace by the time it would be released in the early 1990s. In response, a "Superbus" study group was formed in November 1987. Another working group of the standards association of the Institute of Electrical and Electronics Engineers (IEEE) spun off to form a standard targeted at this market in July 1988. It was essentially a subset of Futurebus features that could be easily implemented at high speed, along with minor additions to make it easier to connect to other systems, such as VMEbus. Most of the developers had their background from high-speed computer buses. Representatives from companies in the computer industry and research community included Amdahl, Apple Computer, BB&N, Hewlett-Packard, CERN, Dolphin Server Technology, Cray Research, Sequent, AT&T, Digital Equipment Corporation, McDonnell Douglas, National Semiconductor, Stanford Linear Accelerator Center, Tektronix, Texas Instruments, Unisys, University of Oslo, University of Wisconsin. The original intent was a single standard for all buses in the computer. The working group soon came up with the idea of using point-to-point communication in the form of insertion rings. This avoided the lumped capacitance, limited physical length/speed of light problems and stub reflections in addition to allowing parallel transactions. The use of insertion rings is credited to Manolis Katevenis who suggested it at one of the early meetings of the working group. The working group for developing the standard was led by David B. Gustavson (chair) and David V. James (Vice Chair). David V. James was a major contributor for writing the specifications including the executable C-code. Stein Gjessing’s group at the University of Oslo used formal methods to verify the coherence protocol and Dolphin Server Technology implemented a node controller chip including the cache coherence logic. Different versions and derivatives of SCI were implemented by companies like Dolphin Interconnect Solutions, Convex, Data General AViiON (using cache controller and link controller chips from Dolphin), Sequent and Cray Research. Dolphin Interconnect Solutions implemented a PCI and PCI-Express connected derivative of SCI that provides non-coherent shared memory access. This implementation was used by Sun Microsystems for its high-end clusters, Thales Group and several others including volume applications for message passing within HPC clustering and medical imaging. SCI was often used to implement non-uniform memory access architectures. It was also used by Sequent Computer Systems as the processor memory bus in their NUMA-Q systems. Numascale developed a derivative to connect with coherent HyperTransport. == The standard == The standard defined two interface levels: The physical level that deals with electrical signals, connectors, mechanical and thermal conditions The logical level that describes the address space, data transfer protocols, cache coherence mechanisms, synchronization primitives, control and status registers, and initialization and error recovery facilities. This structure allowed new developments in physical interface technology to be easily adapted without any redesign on the logical level. Scalability for large systems is achieved through a distributed directory-based cache coherence model. (The other popular models for cache coherency are based on system-wide eavesdropping (snooping) of memory transactions – a scheme which is not very scalable.) In SCI each node contains a directory with a pointer to the next node in a linked list that shares a particular cache line. SCI defines a 64-bit flat address space (16 exabytes) where 16 bits are used for identifying a node (65,536 nodes) and 48 bits for address within the node (256 terabytes). A node can contain many processors and/or memory. The SCI standard defines a packet switched network. === Topologies === SCI can be used to build systems with different types of switching topologies from centralized to fully distributed switching: With a central switch, each node is connected to the switch with a ringlet (in this case a two-node ring). In distributed switching systems, each node can be connected to a ring of arbitrary length and either all or some of the nodes can be connected to two or more rings. The most common way to describe these multi-dimensional topologies is k-ary n-cubes (or tori). The SCI standard specification mentions several such topologies as examples. The 2-D torus is a combination of rings in two dimensions. Switching between the two dimensions requires a small switching capability in the node. This can be expanded to three or more dimensions. The concept of folding rings can also be applied to the Torus topologies to avoid any long connection segments. === Transactions === SCI sends information in packets. Each packet consists of an unbroken sequence of 16-bit symbols. The symbol is accompanied by a flag bit. A transition of the flag bit from 0 to 1 indicates the start of a packet. A transition from 1 to 0 occurs 1 (for echoes) or 4 symbols before the packet end. A packet contains a header with address command and status information, payload (from 0 through optional lengths of data) and a CRC check symbol. The first symbol in the packet header contains the destination node address. If the address is not within the domain handled by the receiving node, the packet is passed to the output through the bypass FIFO. In the other case, the packet is fed to a receive queue and may be transferred to a ring in another dimension. All packets are marked when they pass the scrubber (a node is established as scrubber when the ring is initialized). Packets without a valid destination address will be removed when passing the scrubber for the second time to avoid filling the ring with packets that would otherwise circulate indefinitely. === Cache coherence === Cache coherence ensures data consistency in multiprocessor systems. The simplest form applied in earlier systems was based on clearing the cache contents between context switches and disabling the cache for data that were shared between two or more processors. These methods were feasible when the performance difference between the cache and memory were less than one order of magnitude. Modern processors with caches that are more than two orders of magnitude faster than main memory would not perform anywhere near optimal without more sophisticated methods for data consistency. Bus based systems use eavesdropping (snooping) methods since buses are inherently broadcast. Modern systems with point-to point links use broadcast methods with snoop filter options to improve performance. Since broadcast and eavesdropping are inherently non-scalable, these are not used in SCI. Instead, SCI uses a distributed directory-based cache coherence protocol with a linked list of nodes containing processors that share a particular cache line. Each node holds a directory for the main memory of the node with a tag for each line of memory (same line length as the cache line). The memory tag holds a pointer to the head of the linked list and a state code for the line (three states – home, fresh, gone). Associated with each node is also a cache for holding remote data with a directory containing forward and backward pointers to nodes in the linked list sharing the cache line. The tag for the cache has seven states (invalid, only fresh, head fresh, only dirty, head dirty, mid valid, tail valid). The distributed directory is scalable. The overhead for the directory based cache coherence is a constant percentage of the node’s memory and cache. This percentage is in the order of 4% for the memory and 7% for the cache. == Legacy == SCI is a standard for connecting the different resources within a multiprocessor computer system, and it is not as widely known to the public as for example the Ethernet family for connecting different systems. Different system vendors implemented different variants of SCI for their internal system infrastructure. These different implementations interface to very intricate mechanisms in processors and memory systems and each vendor has to preserve some degrees of

  Read more →
• 

  Locally recoverable code

  Locally recoverable codes are a family of error correction codes that were introduced first by D. S. Papailiopoulos and A. G. Dimakis and have been widely studied in information theory due to their applications related to distributive and cloud storage systems. An [ n , k , d , r ] q {\displaystyle [n,k,d,r]_{q}} LRC is an [ n , k , d ] q {\displaystyle [n,k,d]_{q}} linear code such that there is a function f i {\displaystyle f_{i}} that takes as input i {\displaystyle i} and a set of r {\displaystyle r} other coordinates of a codeword c = ( c 1 , … , c n ) ∈ C {\displaystyle c=(c_{1},\ldots ,c_{n})\in C} different from c i {\displaystyle c_{i}} , and outputs c i {\displaystyle c_{i}} . == Overview == Erasure-correcting codes, or simply erasure codes, for distributed and cloud storage systems, are becoming more and more popular as a result of the present spike in demand for cloud computing and storage services. This has inspired researchers in the fields of information and coding theory to investigate new facets of codes that are specifically suited for use with storage systems. It is well-known that LRC is a code that needs only a limited set of other symbols to be accessed in order to restore every symbol in a codeword. This idea is very important for distributed and cloud storage systems since the most common error case is when one storage node fails (erasure). The main objective is to recover as much data as possible from the fewest additional storage nodes in order to restore the node. Hence, Locally Recoverable Codes are crucial for such systems. The following definition of the LRC follows from the description above: an [ n , k , r ] {\displaystyle [n,k,r]} -Locally Recoverable Code (LRC) of length n {\displaystyle n} is a code that produces an n {\displaystyle n} -symbol codeword from k {\displaystyle k} information symbols, and for any symbol of the codeword, there exist at most r {\displaystyle r} other symbols such that the value of the symbol can be recovered from them. The locality parameter satisfies 1 ≤ r ≤ k {\displaystyle 1\leq r\leq k} because the entire codeword can be found by accessing k {\displaystyle k} symbols other than the erased symbol. Furthermore, Locally Recoverable Codes, having the minimum distance d {\displaystyle d} , can recover d − 1 {\displaystyle d-1} erasures. == Definition == Let C {\displaystyle C} be a [ n , k , d ] q {\displaystyle [n,k,d]_{q}} linear code. For i ∈ { 1 , … , n } {\displaystyle i\in \{1,\ldots ,n\}} , let us denote by r i {\displaystyle r_{i}} the minimum number of other coordinates we have to look at to recover an erasure in coordinate i {\displaystyle i} . The number r i {\displaystyle r_{i}} is said to be the locality of the i {\displaystyle i} -th coordinate of the code. The locality of the code is defined as An [ n , k , d , r ] q {\displaystyle [n,k,d,r]_{q}} locally recoverable code (LRC) is an [ n , k , d ] q {\displaystyle [n,k,d]_{q}} linear code C ∈ F q n {\displaystyle C\in \mathbb {F} _{q}^{n}} with locality r {\displaystyle r} . Let C {\displaystyle C} be an [ n , k , d ] q {\displaystyle [n,k,d]_{q}} -locally recoverable code. Then an erased component can be recovered linearly, i.e. for every i ∈ { 1 , … , n } {\displaystyle i\in \{1,\ldots ,n\}} , the space of linear equations of the code contains elements of the form x i = f ( x i 1 , … , x i r ) {\displaystyle x_{i}=f(x_{i_{1}},\ldots ,x_{i_{r}})} , where i j ≠ i {\displaystyle i_{j}\neq i} . == Optimal locally recoverable codes == Theorem Let n = ( r + 1 ) s {\displaystyle n=(r+1)s} and let C {\displaystyle C} be an [ n , k , d ] q {\displaystyle [n,k,d]_{q}} -locally recoverable code having s {\displaystyle s} disjoint locality sets of size r + 1 {\displaystyle r+1} . Then An [ n , k , d , r ] q {\displaystyle [n,k,d,r]_{q}} -LRC C {\displaystyle C} is said to be optimal if the minimum distance of C {\displaystyle C} satisfies == Tamo–Barg codes == Let f ∈ F q [ x ] {\displaystyle f\in \mathbb {F} _{q}[x]} be a polynomial and let ℓ {\displaystyle \ell } be a positive integer. Then f {\displaystyle f} is said to be ( r {\displaystyle r} , ℓ {\displaystyle \ell } )-good if • f {\displaystyle f} has degree r + 1 {\displaystyle r+1} , • there exist distinct subsets A 1 , … , A ℓ {\displaystyle A_{1},\ldots ,A_{\ell }} of F q {\displaystyle \mathbb {F} _{q}} such that – for any i ∈ { 1 , … , ℓ } {\displaystyle i\in \{1,\ldots ,\ell \}} , f ( A i ) = { t i } {\displaystyle f(A_{i})=\{t_{i}\}} for some t i ∈ F q {\displaystyle t_{i}\in \mathbb {F} _{q}} , i.e., f {\displaystyle f} is constant on A i {\displaystyle A_{i}} , – # A i = r + 1 {\displaystyle \#A_{i}=r+1} , – A i ∩ A j = ∅ {\displaystyle A_{i}\cap A_{j}=\varnothing } for any i ≠ j {\displaystyle i\neq j} . We say that { A 1 , … , A ℓ {\displaystyle A_{1},\ldots ,A_{\ell }} } is a splitting covering for f {\displaystyle f} . === Tamo–Barg construction === The Tamo–Barg construction utilizes good polynomials. • Suppose that a ( r , ℓ ) {\displaystyle (r,\ell )} -good polynomial f ( x ) {\displaystyle f(x)} over F q {\displaystyle \mathbb {F} _{q}} is given with splitting covering i ∈ { 1 , … , ℓ } {\displaystyle i\in \{1,\ldots ,\ell \}} . • Let s ≤ ℓ − 1 {\displaystyle s\leq \ell -1} be a positive integer. • Consider the following F q {\displaystyle \mathbb {F} _{q}} -vector space of polynomials V = { ∑ i = 0 s g i ( x ) f ( x ) i : deg ⁡ ( g i ( x ) ) ≤ deg ⁡ ( f ( x ) ) − 2 } . {\displaystyle V=\left\{\sum _{i=0}^{s}g_{i}(x)f(x)^{i}:\deg(g_{i}(x))\leq \deg(f(x))-2\right\}.} • Let T = ⋃ i = 1 ℓ A i {\textstyle T=\bigcup _{i=1}^{\ell }A_{i}} . • The code { ev T ⁡ ( g ) : g ∈ V } {\displaystyle \{\operatorname {ev} _{T}(g):g\in V\}} is an ( ( r + 1 ) ℓ , ( s + 1 ) r , d , r ) {\displaystyle ((r+1)\ell ,(s+1)r,d,r)} -optimal locally coverable code, where ev T {\displaystyle \operatorname {ev} _{T}} denotes evaluation of g {\displaystyle g} at all points in the set T {\displaystyle T} . === Parameters of Tamo–Barg codes === • Length. The length is the number of evaluation points. Because the sets A i {\displaystyle A_{i}} are disjoint for i ∈ { 1 , … , ℓ } {\displaystyle i\in \{1,\ldots ,\ell \}} , the length of the code is | T | = ( r + 1 ) ℓ {\displaystyle |T|=(r+1)\ell } . • Dimension. The dimension of the code is ( s + 1 ) r {\displaystyle (s+1)r} , for s {\displaystyle s} ≤ ℓ − 1 {\displaystyle \ell -1} , as each g i {\displaystyle g_{i}} has degree at most deg ⁡ ( f ( x ) ) − 2 {\displaystyle \deg(f(x))-2} , covering a vector space of dimension deg ⁡ ( f ( x ) ) − 1 = r {\displaystyle \deg(f(x))-1=r} , and by the construction of V {\displaystyle V} , there are s + 1 {\displaystyle s+1} distinct g i {\displaystyle g_{i}} . • Distance. The distance is given by the fact that V ⊆ F q [ x ] ≤ k {\displaystyle V\subseteq \mathbb {F} _{q}[x]_{\leq k}} , where k = r + 1 − 2 + s ( r + 1 ) {\displaystyle k=r+1-2+s(r+1)} , and the obtained code is the Reed-Solomon code of degree at most k {\displaystyle k} , so the minimum distance equals ( r + 1 ) ℓ − ( ( r + 1 ) − 2 + s ( r + 1 ) ) {\displaystyle (r+1)\ell -((r+1)-2+s(r+1))} . • Locality. After the erasure of the single component, the evaluation at a i ∈ A i {\displaystyle a_{i}\in A_{i}} , where | A i | = r + 1 {\displaystyle |A_{i}|=r+1} , is unknown, but the evaluations for all other a ∈ A i {\displaystyle a\in A_{i}} are known, so at most r {\displaystyle r} evaluations are needed to uniquely determine the erased component, which gives us the locality of r {\displaystyle r} . To see this, g {\displaystyle g} restricted to A j {\displaystyle A_{j}} can be described by a polynomial h {\displaystyle h} of degree at most deg ⁡ ( f ( x ) ) − 2 = r + 1 − 2 = r − 1 {\displaystyle \deg(f(x))-2=r+1-2=r-1} thanks to the form of the elements in V {\displaystyle V} (i.e., thanks to the fact that f {\displaystyle f} is constant on A j {\displaystyle A_{j}} , and the g i {\displaystyle g_{i}} 's have degree at most deg ⁡ ( f ( x ) ) − 2 {\displaystyle \deg(f(x))-2} ). On the other hand | A j ∖ { a j } | = r {\displaystyle |A_{j}\backslash \{a_{j}\}|=r} , and r {\displaystyle r} evaluations uniquely determine a polynomial of degree r − 1 {\displaystyle r-1} . Therefore h {\displaystyle h} can be constructed and evaluated at a j {\displaystyle a_{j}} to recover g ( a j ) {\displaystyle g(a_{j})} . === Example of Tamo–Barg construction === We will use x 5 ∈ F 41 [ x ] {\displaystyle x^{5}\in \mathbb {F} _{41}[x]} to construct [ 15 , 8 , 6 , 4 ] {\displaystyle [15,8,6,4]} -LRC. Notice that the degree of this polynomial is 5, and it is constant on A i {\displaystyle A_{i}} for i ∈ { 1 , … , 8 } {\displaystyle i\in \{1,\ldots ,8\}} , where A 1 = { 1 , 10 , 16 , 18 , 37 } {\displaystyle A_{1}=\{1,10,16,18,37\}} , A 2 = 2 A 1 {\displaystyle A_{2}=2A_{1}} , A 3 = 3 A 1 {\displaystyle A_{3}=3A_{1}} , A 4 = 4 A 1 {\displaystyle A_{4}=4A_{1}} , A 5 = 5 A 1 {\displaystyle A_{5}=5A_{1}} , A 6 = 6 A 1 {\displaystyle A_{6}=6A_{1}}

  Read more →
• 

  Data grid

  A data grid is an architecture or set of services that allows users to access, modify and transfer extremely large amounts of geographically distributed data for research purposes. Data grids make this possible through a host of middleware applications and services that pull together data and resources from multiple administrative domains and then present it to users upon request. The data in a data grid can be located at a single site or multiple sites where each site can be its own administrative domain governed by a set of security restrictions as to who may access the data. Likewise, multiple replicas of the data may be distributed throughout the grid outside their original administrative domain and the security restrictions placed on the original data for who may access it must be equally applied to the replicas. Specifically developed data grid middleware is what handles the integration between users and the data they request by controlling access while making it available as efficiently as possible. == Middleware == Middleware provides all the services and applications necessary for efficient management of datasets and files within the data grid while providing users quick access to the datasets and files. There is a number of concepts and tools that must be available to make a data grid operationally viable. However, at the same time not all data grids require the same capabilities and services because of differences in access requirements, security and location of resources in comparison to users. In any case, most data grids will have similar middleware services that provide for a universal name space, data transport service, data access service, data replication and resource management service. When taken together, they are key to the data grids functional capabilities. === Universal namespace === Since sources of data within the data grid will consist of data from multiple separate systems and networks using different file naming conventions, it would be difficult for a user to locate data within the data grid and know they retrieved what they needed based solely on existing physical file names (PFNs). A universal or unified name space makes it possible to create logical file names (LFNs) that can be referenced within the data grid that map to PFNs. When an LFN is requested or queried, all matching PFNs are returned to include possible replicas of the requested data. The end user can then choose from the returned results the most appropriate replica to use. This service is usually provided as part of a management system known as a Storage Resource Broker (SRB). Information about the locations of files and mappings between the LFNs and PFNs may be stored in a metadata or replica catalogue. The replica catalogue would contain information about LFNs that map to multiple replica PFNs. === Data transport service === Another middleware service is that of providing for data transport or data transfer. Data transport will encompass multiple functions that are not just limited to the transfer of bits, to include such items as fault tolerance and data access. Fault tolerance can be achieved in a data grid by providing mechanisms that ensures data transfer will resume after each interruption until all requested data is received. There are multiple possible methods that might be used to include starting the entire transmission over from the beginning of the data to resuming from where the transfer was interrupted. As an example, GridFTP provides for fault tolerance by sending data from the last acknowledged byte without starting the entire transfer from the beginning. The data transport service also provides for the low-level access and connections between hosts for file transfer. The data transport service may use any number of modes to implement the transfer to include parallel data transfer where two or more data streams are used over the same channel or striped data transfer where two or more steams access different blocks of the file for simultaneous transfer to also using the underlying built-in capabilities of the network hardware or specifically developed protocols to support faster transfer speeds. The data transport service might optionally include a network overlay function to facilitate the routing and transfer of data as well as file I/O functions that allow users to see remote files as if they were local to their system. The data transport service hides the complexity of access and transfer between the different systems to the user so it appears as one unified data source. === Data access service === Data access services work hand in hand with the data transfer service to provide security, access controls and management of any data transfers within the data grid. Security services provide mechanisms for authentication of users to ensure they are properly identified. Common forms of security for authentication can include the use of passwords or Kerberos (protocol). Authorization services are the mechanisms that control what the user is able to access after being identified through authentication. Common forms of authorization mechanisms can be as simple as file permissions. However, need for more stringent controlled access to data is done using Access Control Lists (ACLs), Role-Based Access Control (RBAC) and Tasked-Based Authorization Controls (TBAC). These types of controls can be used to provide granular access to files to include limits on access times, duration of access to granular controls that determine which files can be read or written to. The final data access service that might be present to protect the confidentiality of the data transport is encryption. The most common form of encryption for this task has been the use of SSL while in transport. While all of these access services operate within the data grid, access services within the various administrative domains that host the datasets will still stay in place to enforce access rules. The data grid access services must be in step with the administrative domains access services for this to work. === Data replication service === To meet the needs for scalability, fast access and user collaboration, most data grids support replication of datasets to points within the distributed storage architecture. The use of replicas allows multiple users faster access to datasets and the preservation of bandwidth since replicas can often be placed strategically close to or within sites where users need them. However, replication of datasets and creation of replicas is bound by the availability of storage within sites and bandwidth between sites. The replication and creation of replica datasets is controlled by a replica management system. The replica management system determines user needs for replicas based on input requests and creates them based on availability of storage and bandwidth. All replicas are then cataloged or added to a directory based on the data grid as to their location for query by users. In order to perform the tasks undertaken by the replica management system, it needs to be able to manage the underlying storage infrastructure. The data management system will also ensure the timely updates of changes to replicas are propagated to all nodes. ==== Replication update strategy ==== There are a number of ways the replication management system can handle the updates of replicas. The updates may be designed around a centralized model where a single master replica updates all others, or a decentralized model, where all peers update each other. The topology of node placement may also influence the updates of replicas. If a hierarchy topology is used then updates would flow in a tree like structure through specific paths. In a flat topology it is entirely a matter of the peer relationships between nodes as to how updates take place. In a hybrid topology consisting of both flat and hierarchy topologies updates may take place through specific paths and between peers. ==== Replication placement strategy ==== There are a number of ways the replication management system can handle the creation and placement of replicas to best serve the user community. If the storage architecture supports replica placement with sufficient site storage, then it becomes a matter of the needs of the users who access the datasets and a strategy for placement of replicas. There have been numerous strategies proposed and tested on how to best manage replica placement of datasets within the data grid to meet user requirements. There is not one universal strategy that fits every requirement the best. It is a matter of the type of data grid and user community requirements for access that will determine the best strategy to use. Replicas can even be created where the files are encrypted for confidentiality that would be useful in a research project dealing with medical files. The following section contains several strategies for replica placement. ===== Dynamic replication ===== Dynam

  Read more →
• 

  Energy-based model

  An energy-based model (EBM), also called Canonical Ensemble Learning (CEL) or Learning via Canonical Ensemble (LCE), is an application of canonical ensemble formulation from statistical physics for learning from data. The approach prominently appears in generative artificial intelligence. EBMs provide a unified framework for many probabilistic and non-probabilistic approaches to such learning, particularly for training graphical and other structured models. An EBM learns the characteristics of a target dataset and generates a similar but larger dataset. EBMs detect the latent variables of a dataset and generate new datasets with a similar distribution. Energy-based generative neural networks is a class of generative models, which aim to learn explicit probability distributions of data in the form of energy-based models, the energy functions of which are parameterized by modern deep neural networks. Boltzmann machines are a special form of energy-based models with a specific parametrization of the energy. == Description == For a given input x {\displaystyle x} , the model describes an energy E θ ( x ) {\displaystyle E_{\theta }(x)} such that the Boltzmann distribution P θ ( x ) = e − β E θ ( x ) Z ( θ ) {\displaystyle P_{\theta }(x)={e^{-\beta E_{\theta }(x)} \over Z(\theta )}} is a probability (density), and typically β = 1 {\displaystyle \beta =1} . Since the normalization constant: Z ( θ ) := ∫ x ∈ X e − β E θ ( x ) d x {\displaystyle Z(\theta ):=\int _{x\in X}e^{-\beta E_{\theta }(x)}dx} (also known as the partition function) depends on all the Boltzmann factors of all possible inputs x {\displaystyle x} , it cannot be easily computed or reliably estimated during training simply using standard maximum likelihood estimation. However, for maximizing the likelihood during training, the gradient of the log-likelihood of a single training example x {\displaystyle x} is given by using the chain rule: ∂ θ log ⁡ ( P θ ( x ) ) = E x ′ ∼ P θ [ ∂ θ E θ ( x ′ ) ] − ∂ θ E θ ( x ) ( ∗ ) {\displaystyle \partial _{\theta }\log \left(P_{\theta }(x)\right)=\mathbb {E} _{x'\sim P_{\theta }}[\partial _{\theta }E_{\theta }(x')]-\partial _{\theta }E_{\theta }(x)\,()} The expectation in the above formula for the gradient can be approximately estimated by drawing samples x ′ {\displaystyle x'} from the distribution P θ {\displaystyle P_{\theta }} using Markov chain Monte Carlo (MCMC). Early energy-based models, such as the 2003 Boltzmann machine by Hinton, estimated this expectation via blocked Gibbs sampling. Newer approaches make use of more efficient Stochastic Gradient Langevin Dynamics (LD), drawing samples using: x 0 ′ ∼ P 0 , x i + 1 ′ = x i ′ − α 2 ∂ E θ ( x i ′ ) ∂ x i ′ + ϵ {\displaystyle x_{0}'\sim P_{0},x_{i+1}'=x_{i}'-{\frac {\alpha }{2}}{\frac {\partial E_{\theta }(x_{i}')}{\partial x_{i}'}}+\epsilon } , where ϵ ∼ N ( 0 , α ) {\displaystyle \epsilon \sim {\mathcal {N}}(0,\alpha )} . A replay buffer of past values x i ′ {\displaystyle x_{i}'} is used with LD to initialize the optimization module. The parameters θ {\displaystyle \theta } of the neural network are therefore trained in a generative manner via MCMC-based maximum likelihood estimation: the learning process follows an "analysis by synthesis" scheme, where within each learning iteration, the algorithm samples the synthesized examples from the current model by a gradient-based MCMC method (e.g., Langevin dynamics or Hybrid Monte Carlo), and then updates the parameters θ {\displaystyle \theta } based on the difference between the training examples and the synthesized ones – see equation ( ∗ ) {\displaystyle ()} . This process can be interpreted as an alternating mode seeking and mode shifting process, and also has an adversarial interpretation. Essentially, the model learns a function E θ {\displaystyle E_{\theta }} that associates low energies to correct values, and higher energies to incorrect values. After training, given a converged energy model E θ {\displaystyle E_{\theta }} , the Metropolis–Hastings algorithm can be used to draw new samples. The acceptance probability is given by: P a c c ( x i → x ∗ ) = min ( 1 , P θ ( x ∗ ) P θ ( x i ) ) . {\displaystyle P_{acc}(x_{i}\to x^{})=\min \left(1,{\frac {P_{\theta }(x^{})}{P_{\theta }(x_{i})}}\right).} == History == The term "energy-based models" was first coined in a 2003 JMLR paper where the authors defined a generalisation of independent components analysis to the overcomplete setting using EBMs. Other early work on EBMs proposed models that represented energy as a composition of latent and observable variables. == Characteristics == EBMs demonstrate useful properties: Simplicity and stability. The EBM is the only object that needs to be designed and trained. Separate networks need not be trained to ensure balance. Adaptive computation time. An EBM can generate sharp, diverse samples or (more quickly) coarse, less diverse samples. Given infinite time, this procedure produces true samples. Flexibility. In Variational Autoencoders (VAE) and flow-based models, the generator learns a map from a continuous space to a (possibly) discontinuous space containing different data modes. EBMs can learn to assign low energies to disjoint regions (multiple modes). Adaptive generation. EBM generators are implicitly defined by the probability distribution, and automatically adapt as the distribution changes (without training), allowing EBMs to address domains where generator training is impractical, as well as minimizing mode collapse and avoiding spurious modes from out-of-distribution samples. Compositionality. Individual models are unnormalized probability distributions, allowing models to be combined through product of experts or other hierarchical techniques. == Experimental results == On image datasets such as CIFAR-10 and ImageNet 32x32, an EBM model generated high-quality images relatively quickly. It supported combining features learned from one type of image for generating other types of images. It was able to generalize using out-of-distribution datasets, outperforming flow-based and autoregressive models. EBM was relatively resistant to adversarial perturbations, behaving better than models explicitly trained against them with training for classification. == Applications == Target applications include natural language processing, robotics and computer vision. The first energy-based generative neural network is the generative ConvNet proposed in 2016 for image patterns, where the neural network is a convolutional neural network. The model has been generalized to various domains to learn distributions of videos, and 3D voxels. They are made more effective in their variants. They have proven useful for data generation (e.g., image synthesis, video synthesis, 3D shape synthesis, etc.), data recovery (e.g., recovering videos with missing pixels or image frames, 3D super-resolution, etc), data reconstruction (e.g., image reconstruction and linear interpolation ). == Alternatives == EBMs compete with techniques such as variational autoencoders (VAEs), generative adversarial networks (GANs) or normalizing flows. == Extensions == === Joint energy-based models === Joint energy-based models (JEM), proposed in 2020 by Grathwohl et al., allow any classifier with softmax output to be interpreted as energy-based model. The key observation is that such a classifier is trained to predict the conditional probability p θ ( y | x ) = e f → θ ( x ) [ y ] ∑ j = 1 K e f → θ ( x ) [ j ] for y = 1 , … , K and f → θ = ( f 1 , … , f K ) ∈ R K , {\displaystyle p_{\theta }(y|x)={\frac {e^{{\vec {f}}_{\theta }(x)[y]}}{\sum _{j=1}^{K}e^{{\vec {f}}_{\theta }(x)[j]}}}\ \ {\text{ for }}y=1,\dotsc ,K{\text{ and }}{\vec {f}}_{\theta }=(f_{1},\dotsc ,f_{K})\in \mathbb {R} ^{K},} where f → θ ( x ) [ y ] {\displaystyle {\vec {f}}_{\theta }(x)[y]} is the y-th index of the logits f → {\displaystyle {\vec {f}}} corresponding to class y. Without any change to the logits it was proposed to reinterpret the logits to describe a joint probability density: p θ ( y , x ) = e f → θ ( x ) [ y ] Z ( θ ) , {\displaystyle p_{\theta }(y,x)={\frac {e^{{\vec {f}}_{\theta }(x)[y]}}{Z(\theta )}},} with unknown partition function Z ( θ ) {\displaystyle Z(\theta )} and energy E θ ( x , y ) = − f θ ( x ) [ y ] {\displaystyle E_{\theta }(x,y)=-f_{\theta }(x)[y]} . By marginalization, we obtain the unnormalized density p θ ( x ) = ∑ y p θ ( y , x ) = ∑ y e f → θ ( x ) [ y ] Z ( θ ) =: e − E θ ( x ) , {\displaystyle p_{\theta }(x)=\sum _{y}p_{\theta }(y,x)=\sum _{y}{\frac {e^{{\vec {f}}_{\theta }(x)[y]}}{Z(\theta )}}=:e^{-E_{\theta }(x)},} therefore, E θ ( x ) = − log ⁡ ( ∑ y e f → θ ( x ) [ y ] Z ( θ ) ) , {\displaystyle E_{\theta }(x)=-\log \left(\sum _{y}{\frac {e^{{\vec {f}}_{\theta }(x)[y]}}{Z(\theta )}}\right),} so that any classifier can be used to define an energy function E θ ( x ) {\displaystyle E_{\theta }(x)} .

  Read more →
• 

  Batch cryptography

  Batch cryptography is a field of cryptology focused on the design of cryptographic protocols that perform operations—such as encryption, decryption, key exchange, and authentication—on multiple inputs simultaneously, rather than processing each input individually. Batching cryptographic operations can significantly reduce the marginal cost of handling individual inputs—a principle that was first introduced by Amos Fiat in 1989.

  Read more →
• 

  Corporate surveillance

  Corporate surveillance describes the practice of businesses monitoring and extracting information from their users, clients, or staff. This information may consist of online browsing history, email correspondence, phone calls, location data, and other private details. Acts of corporate surveillance frequently look to boost results, detect potential security problems, or adjust advertising strategies. These practices have been criticized for violating ethical standards and invading personal privacy. Critics and privacy activists have called for businesses to incorporate rules and transparency surrounding their monitoring methods to ensure they are not misusing their position of authority or breaching regulatory standards. Monitoring can feel intrusive and give the impression that the business does not promote ethical behavior among its personnel. Staff satisfaction, productivity, and staff turnover may all suffer as a result of the invasion of privacy. == Monitoring methods == Employers may be authorized to gather information through keystroke logging and mouse tracking, which involves recording the keys individuals interact with and cursor position on computers. In cases where employment contracts permit it, they may also monitor webcam activity on company-provided computers. Employers may be able to view the emails sent from business accounts and may be able to see the websites visited when using a corporate internet connection. The screenshot capability is another tool that enables companies to see what remote workers are doing. This feature, which can be found in tracking software, takes screenshots throughout the day at predetermined or arbitrary intervals. Additionally, people who don't work in offices are observed. For instance, it has been claimed that Amazon has incorporated tracking technology to monitor warehouse staff and delivery drivers. == Use of collected information == Information collected by corporations can be used for a variety of uses including marketing research, targeting advertising, fraud detection and prevention, ensuring policy adherence, preventing lawsuits, and safeguarding records and company assets. == Privacy concerns == Concerns over corporate privacy have become more important due to companies collection and manipulation of personal data. Since these practices have been recognized there has been a rising concern about both the security and the possible mishandling of the data accumulated. Social Media data collection and monitoring has been one of the most concerned areas regarding corporate surveillance. Recently, many employers on CareerBuilder have checked their potential candidates' social media activities before the hiring process. This approach can be excusable since it is important to be aware of a future employee or applicant's online presence, and how it might affect the company's reputation in the future. This is crucial since employers are often made legally responsible for their worker's digital actions. These data can also be used to enact political gains. The Facebook-Cambridge Analytica data scandal in 2018 revealed that its British branch to have surreptitiously sold American psychological data to the Trump campaign. This information was supposed to be private, but Facebook's inability to protect user information had reportedly not been a top priority of the company at the time. == Laws and regulations == The National Labor and Relations Act (NLRA) safeguards workplace democracy by giving workers in the private sector the basic freedom to demand better working conditions and choice of representation without fear of retaliation. General Data Protection Regulation (GDPR) outlines the broad responsibilities of data controllers and the "processors" that handle personal data on their behalf. They must adopt the necessary security measures in accordance with the risk involved in the data processing operations they carry out.[1] Electronics Communication Privacy Act (ECPA), as amended, provides protection for electronic, oral, and wire communications while they are being created, while they are being sent, and while they are being stored on computers. Email, phone calls, and electronically stored data are covered by the Act. == Sale of customer data == If it is business intelligence, data collected on individuals and groups can be sold to other corporations, so that they can use it for the aforementioned purpose. It can be used for direct marketing purposes, such as targeted advertisements on Google and Yahoo. These ads are tailored to the individual user of the search engine by analyzing their search history and emails (if they use free webmail services). For example, the world's most popular web search engine stores identifying information for each web search. Google stores an IP address and the search phrase used in a database for up to 2 years. Google also scans the content of emails of users of its Gmail webmail service, in order to create targeted advertising based on what people are talking about in their personal email correspondences. Google is, by far, the largest web advertising agency. Their revenue model is based on receiving payments from advertisers for each page-visit resulting from a visitor clicking on a Google AdWords ad, hosted either on a Google service or a third-party website. Millions of sites place Google's advertising banners and links on their websites, in order to share this profit from visitors who click on the ads. Each page containing Google advertisements adds, reads, and modifies cookies on each visitor's computer. These cookies track the user across all of these sites, and gather information about their web surfing habits, keeping track of which sites they visit, and what they do when they are on these sites. This information, along with the information from their email accounts, and search engine histories, is stored by Google to use for building a profile of the user to deliver better-targeted advertising. == Surveillance of workers == In 1993, David Steingard and Dale Fitzgibbons argued that modern management, far from empowering workers, had features of neo-Taylorism, where teamwork perpetuated surveillance and control. They argued that employees had become their own "thought police" and the team gaze was the equivalent of Bentham's panopticon guard tower. A critical evaluation of the Hawthorne Plant experiments has in turn given rise to the notion of a Hawthorne effect, where workers increase their productivity in response to their awareness of being observed or because they are gratified for being chosen to participate in a project. According to the American Management Association and the ePolicy Institute, who undertook a quantitative survey in 2007 about electronic monitoring and surveillance with approximately 300 US companies, "more than one fourth of employers have fired workers for misusing email and nearly one third have fired employees for misusing the Internet." Furthermore, about 30 percent of the companies had also fired employees for usage of "inappropriate or offensive language" and "viewing, downloading, or uploading inappropriate/offensive content." More than 40 percent of the companies monitor email traffic of their workers, and 66 percent of corporations monitor Internet connections. In addition, most companies use software to block websites such as sites with games, social networking, entertainment, shopping, and sports. The American Management Association and the ePolicy Institute also stress that companies track content that is being written about them, for example by monitoring blogs and social media, and scanning all files that are stored in a filesystem. == Government use of corporate surveillance data == The United States government often gains access to corporate databases, either by producing a warrant for it, or by asking. The Department of Homeland Security has openly stated that it uses data collected from consumer credit and direct marketing agencies—such as Google—for augmenting the profiles of individuals that it is monitoring. The US government has gathered information from grocery store discount card programs, which track customers' shopping patterns and store them in databases, in order to look for terrorists by analyzing shoppers' buying patterns. == Corporate surveillance of citizens == According to Dennis Broeders, "Big Brother is joined by big business". He argues that corporations are in any event interested in data on their potential customers and that placing some forms of surveillance in the hands of companies, results in companies owning video surveillance data for stores and public places. The commercial availability of surveillance systems has led to their rapid spread. Therefore it is almost impossible for citizens to maintain their anonymity. When businesses can monitor their customers, such customers run the risk of facing prejudice when applying for housing, loans, jobs, and other economic opportun

  Read more →