AI App Quora

AI App Quora — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

• 

  GoodRx

  GoodRx Holdings, Inc. is an American healthcare company that operates a telemedicine platform and free-to-use website and mobile app that track prescription drug prices in the United States and provide drug coupons for discounts on medications. GoodRx compares prescription drug prices at more than 75,000 pharmacies in the United States. The platform allows users to consult a doctor online and obtain a prescription for certain types of medications. == History == === Financial performance === GoodRx was founded in Santa Monica, California in 2011. GoodRx experienced substantial growth in net income in 2017 ($9 million), 2018 ($44 million), and 2019 ($66 million), but recorded a loss of $293.6 million in 2020 due to IPO-related expenses. In September 2020, GoodRx went public on the Nasdaq under the ticker symbol GDRX. The company priced its initial public offering at $33 per share, above the expected range of $24 to $28, raising more than $1.1 billion at an initial valuation of approximately $12.7 billion. In the first half of 2020, the company reported revenues of $257 million and net income of $55 million. GoodRx generated $745.4 million in revenue for the full year 2021, a 35.36% increase over 2020. During the first half of 2021, the company’s share price declined by 10.7%. The decline was attributed to increased competition in online pharmacy services and slower user growth. GoodRx reported full-year revenue of $766.6 million, with adjusted EBITDA reaching $213.5 million, exceeding guidance in the fourth quarter. GoodRx reported that 41% of prescriptions filled using its coupons were newly adherent, meaning they would not have been filled without the service. GoodRx reported a full-year 2023 revenue of $750.3 million, a decrease of 2.1% from 2022. However, its fourth-quarter revenue increased by 7% year-over-year. GoodRx achieved an Adjusted EBITDA of $217.4 million for the year and an Adjusted EBITDA Margin of 28.6%. In 2024, GoodRx achieved 6% revenue growth with $792.3 million for the full year and turned a net loss into a positive net income of $16.4 million. The company also demonstrated strong operational efficiency, with a 32.8% increase in full-year Adjusted EBITDA. In Q2 2025, GoodRx reported revenue of $203.1 million, a 1.2% increase from the previous year, and a net income of $12.8 million, a significant 92% jump, which resulted in a 6.3% net income margin. However, prescription transaction revenue declined by 3% due to a decrease in monthly active consumers, but this was offset by strong 32% growth in its Pharma Manufacturer Solutions business. GoodRx also saw a 7% decrease in subscription revenue. === Mergers and acquisitions === In 2019, GoodRx acquired HeyDoctor, a telemedicine company, to integrate virtual healthcare services into the platform. In 2021, a health video content producer, HealthiNation was acquired by GoodRx, which helped provide consumers with health information and offered pharmaceutical manufacturers new ways to reach relevant audiences. In April 2022, GoodRx acquired VitaCare Prescription Services from TherapeuticsMD to strengthen its pharma manufacturer solutions business. === Partnerships === In 2017, the company announced partnerships with major pharmaceutical companies to negotiate lower prescription drug costs. GoodRx has deep relationships with major pharmacy chains, including Walgreens, Walmart, CVS Caremark, and Publix, to allow customers to use GoodRx discounts and Gold benefits. GoodRx began its partnership with CVS Caremark in July 2023 to automatically apply coupons to insured CVS customers purchasing generic prescriptions at certain locations. In April 2024, GoodRx added Publix into its network, allowing GoodRx Gold members to use their cards at Publix Pharmacies. GoodRx partners with Pharmacy Benefit Management like Caremark, Express Scripts, and MedImpact to apply their savings directly to eligible insurance plans and members. GoodRx partners with companies like Affirm, Benefitfocus, and DoorDash to integrate their services that offer members discounts and financial flexibility for prescriptions. GoodRx also partners with organizations like the American Academy of Family Physicians Foundation to support broader access to care. In October 2022, GoodRx launched Provider Mode, which allows healthcare providers to use the app to compare costs of drugs for patients based on different payment methods and drug alternatives. In 2025, GoodRx partnered with Novo Nordisk to offer discounted cash-pay access to semaglutide products like Ozempic and Wegovy through its platform and participating pharmacies. == Products and services == GoodRx started its telemedicine service GoodRx Care in September 2019. It lets people talk to a licensed provider online for common issues and get prescriptions even if they don't have insurance. They also run condition-specific subscription plans that bundle online doctor visits, FDA-approved meds, and home delivery into one monthly payment. On the weight management side, GoodRx offers prescriptions for GLP-1 drugs like semaglutide through their telemedicine platform. This got a boost when the oral version of Wegovy became widely available in the US in early 2026. GoodRx works with drug makers like Novo Nordisk to make some medications (including semaglutide options) more affordable for people paying cash. The telemedicine part took off after GoodRx bought HeyDoctor in 2019 and brought their virtual care tools into the main platform. == Key people == The Santa Monica-based startup was founded in September 2011 by Trevor Bezdek and former Facebook executives Doug Hirsch and Scott Marlette. Marlette was one of the first 20 employees at Facebook and built Facebook's photo application. In 2005, Hirsch was the Vice President of Product at Facebook, working closely with Mark Zuckerberg. Bezdek and Hirsch served as co-chief executive officers until April 2023, when they stepped down from those roles and technology executive Scott Wagner was appointed interim chief executive officer. Bezdek became chair of the board, while Hirsch took on the role of chief mission officer. In December 2024, GoodRx announced that healthcare executive Wendy Barnes would become president and chief executive officer effective January 1, 2025. As of 2025, Barnes serves as the company’s CEO, while Trevor Bezdek and Scott Wagner serve as co-chairs of the board, and Doug Hirsch remains involved as a co-founder and senior executive. == Controversy == On February 25, 2020, Consumer Reports published an article stating that GoodRx shared user data—specifically, pseudonymized advertising ID numbers that companies use to track the behavior of web users across websites, the names of the drugs that users browsed, and the pharmacies where users sought to fill prescriptions—with Google, Facebook, and around twenty other Internet-based companies. A few days later, GoodRx released a statement saying that it had made changes to prevent user search data on medical conditions and pharmaceuticals from being shared with Facebook. In March 2020, GoodRx stopped sending data about user prescriptions to Facebook. On February 1, 2023, the Federal Trade Commission fined GoodRx US$1.5 million for violations of the Breach Notification Rule and the Federal Trade Commission Act for allegedly failing to obtain specific, informed, and unambiguous consent from users before disclosing health-related information to Facebook and Google. In November 2024, independent pharmacies filed at least three class action lawsuits against GoodRx and major pharmacy benefit managers. The cases, brought by independent pharmacies in California, Michigan, Pennsylvania, and Rhode Island, allege that GoodRx and the PBMs collaborated to suppress reimbursements for generic prescription drugs. They allege that agreements using GoodRx’s software suppressed reimbursements for generic drugs and violated the Sherman Antitrust Act. The suits claim the practices amount to price fixing which harms small pharmacies while benefiting PBMs and their affiliates. GoodRx settled both the 2023 FTC action and the 2025 class action lawsuit without admitting wrongdoing.

  Read more →
• 

  Photometric stereo

  Photometric stereo is a technique in computer vision for estimating the surface normals of objects by observing that object under different lighting conditions (photometry). It is based on the fact that the amount of light reflected by a surface is dependent on the orientation of the surface in relation to the light source and the observer. By measuring the amount of light reflected into a camera, the space of possible surface orientations is limited. Given enough light sources from different angles, the surface orientation may be constrained to a single orientation or even overconstrained. The technique was originally introduced by Woodham in 1980. The special case where the data is a single image is known as shape from shading, and was analyzed by B. K. P. Horn in 1989. Photometric stereo has since been generalized to many other situations, including extended light sources and non-Lambertian surface finishes. Current research aims to make the method work in the presence of projected shadows, highlights, and non-uniform lighting. Photometric stereo is widely used in various fields, including archaeology, cultural heritage conservation, and quality control. It is now integrated into widely used open-source software, such as Meshroom. == Basic method == Under Woodham's original assumptions — Lambertian reflectance, known point-like distant light sources, and uniform albedo — the problem can be solved by inverting the linear equation I = L ⋅ n {\displaystyle I=L\cdot n} , where I {\displaystyle I} is a (known) vector of m {\displaystyle m} observed intensities, n {\displaystyle n} is the (unknown) surface normal, and L {\displaystyle L} is a (known) 3 × m {\displaystyle 3\times m} matrix of normalized light directions. This model can easily be extended to surfaces with non-uniform albedo, while keeping the problem linear. Taking an albedo reflectivity of k {\displaystyle k} , the formula for the reflected light intensity becomes I = k ( L ⋅ n ) . {\displaystyle I=k(L\cdot n).} If L {\displaystyle L} is square (there are exactly 3 lights) and non-singular, it can be inverted, giving L − 1 I = k n . {\displaystyle L^{-1}I=kn.} Since the normal vector is known to have length 1, k {\displaystyle k} must be the length of the vector k n {\displaystyle kn} , and n {\displaystyle n} is the normalised direction of that vector. If L {\displaystyle L} is not square (there are more than 3 lights), a generalisation of the inverse can be obtained using the Moore–Penrose pseudoinverse, by simply multiplying both sides with L T {\displaystyle L^{T}} , giving L T I = L T k ( L ⋅ n ) , {\displaystyle L^{T}I=L^{T}k(L\cdot n),} ( L T L ) − 1 L T I = k n , {\displaystyle (L^{T}L)^{-1}L^{T}I=kn,} after which the normal vector and albedo can be solved as described above. == Non-Lambertian surfaces == The classical photometric stereo problem concerns itself only with Lambertian surfaces, with perfectly diffuse reflection. This is unrealistic for many types of materials, especially metals, glass and smooth plastics, and will lead to aberrations in the resulting normal vectors. Many methods have been developed to lift this assumption. In this section, a few of these are listed. === Specular reflections === Historically, in computer graphics, the commonly used model to render surfaces started with Lambertian surfaces and progressed first to include simple specular reflections. Computer vision followed a similar course with photometric stereo. Specular reflections were among the first deviations from the Lambertian model. These are a few adaptations that have been developed. Many techniques ultimately rely on modelling the reflectance function of the surface, that is, how much light is reflected in each direction. This reflectance function has to be invertible. The reflected light intensities towards the camera is measured, and the inverse reflectance function is fit onto the measured intensities, resulting in a unique solution for the normal vector. === General BRDFs and beyond === According to the Bidirectional reflectance distribution function (BRDF) model, a surface may distribute the amount of light it receives in any outward direction. This is the most general known model for opaque surfaces. Some techniques have been developed to model (almost) general BRDFs. In practice, all of these require many light sources to obtain reliable data. These are methods in which surfaces with general BRDFs can be measured. Determine the explicit BRDF prior to scanning. To do this, a different surface is required that has the same or a very similar BRDF, of which the actual geometry (or at least the normal vectors for many points on the surface) is already known. The lights are then individually shone upon the known surface, and the amount of reflection into the camera is measured. Using this information, a look-up table can be created that maps reflected intensities for each light source to a list of possible normal vectors. This puts constraints on the possible normal vectors the surface may have, and reduces the photometric stereo problem to an interpolation between measurements. Typical known surfaces to calibrate the look-up table with are spheres for their wide variety of surface orientations. Restricting the BRDF to be symmetrical. If the BRDF is symmetrical, the direction of the light can be restricted to a cone about the direction to the camera. Which cone this is depends on the BRDF itself, the normal vector of the surface, and the measured intensity. Given enough measured intensities and the resulting light directions, these cones can be approximated and therefore the normal vectors of the surface. Some progress has been made towards modelling an even more general surfaces, such as Spatially Varying Bidirectional Distribution Functions (SVBRDF), Bidirectional surface scattering reflectance distribution functions (BSSRDF), and accounting for interreflections. However, such methods are still fairly restrictive in photometric stereo. Better results have been achieved with structured light. == Uncalibrated photometric stereo == Uncalibrated Photometric Stereo is an approach in photometric stereo that aims to reconstruct the 3D shape of an object from images captured under unknown lighting conditions. Unlike classical methods, which often assume controlled or known lighting setups, this approach removes these constraints, making it adaptable to diverse and real-world environments. The advent of deep learning has revolutionized universal PS by replacing handcrafted assumptions with data-driven models. Recent approaches leverage Transformer-based architectures and multi-scale encoder–decoder networks to directly estimate surface normals from input images. Uncalibrated Photometric Stereo is inherently an ill-posed problem, as it attempts to recover 3D shape and lighting conditions simultaneously from images alone. This leads to fundamental ambiguities in the reconstruction process, which manifest as systematic errors in the recovered geometry, including global distortions in the object's overall shape, and misinterpretation of surface orientation, where concave regions may appear convex and vice versa. To address the challenges of uncalibrated photometric stereo, hybrid methods have emerged that combine multi-view stereo and photometric stereo. These approaches leverage the strengths of both techniques, including geometric reliability and resolution.

  Read more →
• 

  Graph cut optimization

  Graph cut optimization is a combinatorial optimization method applicable to a family of functions of discrete variables, named after the concept of cut in the theory of flow networks. Thanks to the max-flow min-cut theorem, determining the minimum cut over a graph representing a flow network is equivalent to computing the maximum flow over the network. Given a pseudo-Boolean function f {\displaystyle f} , if it is possible to construct a flow network with positive weights such that each cut C {\displaystyle C} of the network can be mapped to an assignment of variables x {\displaystyle \mathbf {x} } to f {\displaystyle f} (and vice versa), and the cost of C {\displaystyle C} equals f ( x ) {\displaystyle f(\mathbf {x} )} (up to an additive constant) then it is possible to find the global optimum of f {\displaystyle f} in polynomial time by computing a minimum cut of the graph. The mapping between cuts and variable assignments is done by representing each variable with one node in the graph and, given a cut, each variable will have a value of 0 if the corresponding node belongs to the component connected to the source, or 1 if it belong to the component connected to the sink. Not all pseudo-Boolean functions can be represented by a flow network, and in the general case the global optimization problem is NP-hard. There exist sufficient conditions to characterise families of functions that can be optimised through graph cuts, such as submodular quadratic functions. Graph cut optimization can be extended to functions of discrete variables with a finite number of values, that can be approached with iterative algorithms with strong optimality properties, computing one graph cut at each iteration. Graph cut optimization is an important tool for inference over graphical models such as Markov random fields or conditional random fields, and it has applications in computer vision problems such as image segmentation, denoising, registration and stereo matching. == Representability == A pseudo-Boolean function f : { 0 , 1 } n → R {\displaystyle f:\{0,1\}^{n}\to \mathbb {R} } is said to be representable if there exists a graph G = ( V , E ) {\displaystyle G=(V,E)} with non-negative weights and with source and sink nodes s {\displaystyle s} and t {\displaystyle t} respectively, and there exists a set of nodes V 0 = { v 1 , … , v n } ⊂ V − { s , t } {\displaystyle V_{0}=\{v_{1},\dots ,v_{n}\}\subset V-\{s,t\}} such that, for each tuple of values ( x 1 , … , x n ) ∈ { 0 , 1 } n {\displaystyle (x_{1},\dots ,x_{n})\in \{0,1\}^{n}} assigned to the variables, f ( x 1 , … , x n ) {\displaystyle f(x_{1},\dots ,x_{n})} equals (up to a constant) the value of the flow determined by a minimum cut C = ( S , T ) {\displaystyle C=(S,T)} of the graph G {\displaystyle G} such that v i ∈ S {\displaystyle v_{i}\in S} if x i = 0 {\displaystyle x_{i}=0} and v i ∈ T {\displaystyle v_{i}\in T} if x i = 1 {\displaystyle x_{i}=1} . It is possible to classify pseudo-Boolean functions according to their order, determined by the maximum number of variables contributing to each single term. All first order functions, where each term depends upon at most one variable, are always representable. Quadratic functions f ( x ) = w 0 + ∑ i w i ( x i ) + ∑ i < j w i j ( x i , x j ) . {\displaystyle f(\mathbf {x} )=w_{0}+\sum _{i}w_{i}(x_{i})+\sum _{i 0 {\displaystyle p>0} then w i j k ( x i , x j , x k ) = w i j k ( 0 , 0 , 0 ) + p 1 ( x i − 1 ) + p 2 ( x j − 1 ) + p 3 ( x k − 1 ) + p 23 ( x j − 1 ) x k + p 31 x i ( x k − 1 ) + p 12 ( x i − 1 ) x j − p x i x j x k {\displaystyle w_{ijk}(x_{i},x_{j},x_{k})=w_{ijk}(0,0,0)+p_{1}(x_{i}-1)+p_{2}(x_{j}-1)+p_{3}(x_{k}-1)+p_{23}(x_{j}-1)x_{k}+p_{31}x_{i}(x_{k}-1)+p_{12}(x_{i}-1)x_{j}-px_{i}x_{j}x_{k}} with p 1 = w i j k ( 1 , 0 , 1 ) − w i j k ( 0 , 0 , 1 ) p 2 = w i j k ( 1 , 1 , 0 ) − w i j k ( 1 , 0 , 1 ) p 3 = w i j k ( 0 , 1 , 1 ) − w i j k ( 0 , 1 , 0 ) p 23 = w i j k ( 0 , 0 , 1 ) + w i j k ( 0 , 1 , 0 ) − w i j k ( 0 , 0 , 0 ) − w i j k ( 0 , 1 , 1 ) p 31 = w i j k ( 0 , 0 , 1 ) + w i j k ( 1 , 0 , 0 ) − w i j k ( 0 , 0 , 0 ) − w i j k ( 1 , 0 , 1 ) p 12 = w i j k ( 0 , 1 , 0 ) + w i j k ( 1 , 0 , 0 ) − w i j k ( 0 , 0 , 0 ) − w i j k ( 1 , 1 , 0 ) . {\displaystyle {\begin{aligned}p_{1}&=w_{ijk}(1,0,1)-w_{ijk}(0,0,1)\\p_{2}&=w_{ijk}(1,1,0)-w_{ijk}(1,0,1)\\p_{3}&=w_{ijk}(0,1,1)-w_{ijk}(0,1,0)\\p_{23}&=w_{ijk}(0,0,1)+w_{ijk}(0,1,0)-w_{ijk}(0,0,0)-w_{ijk}(0,1,1)\\p_{31}&=w_{ijk}(0,0,1)+w_{ijk}(1,0,0)-w_{ijk}(0,0,0)-w_{ijk}(1,0,1)\\p_{12}&=w_{ijk}(0,1,0)+w_{ijk}(1,0,0)-w_{ijk}(0,0,0)-w_{ijk}(1,1

  Read more →
• 

  Quantexa

  Quantexa is a UK-based software company that develops artificial intelligence-based applications for data analytics and decision-making. The company was founded in 2016 and is headquartered in London, with operations in North America, Europe, and the Asia-Pacific region. As of 2025, Quantexa reported a valuation of $2.6 billion and provides services to organizations in over 70 countries. Investors include Warburg Pincus, HSBC, and the Ontario Teachers’ Pension Plan. == History == Quantexa was founded in London in 2016 by several co-founders, including Jamie Hutton, Richard Seewald, Imam Hoque, Felix Hoddinott, and Vishal Marria, who also serves as the company's chief executive officer. The company was established to develop tools intended to address limitations in traditional data analysis methods, particularly those related to identifying hidden connections across large datasets. The name "Quantexa" is derived from the company's focus on quantitative methods and data analysis. In 2023, Quantexa acquired Dublin-based AI firm Aylien. In April 2023, the company completed a Series E funding round, raising $129 million at a valuation of approximately $1.8 billion, marking its entry into "unicorn" status. In October 2024, the company reported annual recurring revenue (ARR) exceeding $100 million. In early 2025, Quantexa participated in the World Economic Forum's Unicorn Program, which supports high-growth technology companies. In March 2025, Quantexa completed a Series F funding round of $175 million, led by Teachers' Venture Growth, the venture arm of the Ontario Teachers' Pension Plan. That August, the company was reported to be considering a 2026 IPO. The company formed a partnership with Zurich in October 2025, the first insurer to add its AI-based Decision Intelligence platform to enhance fraud detection.

  Read more →
• 

  3D-Coat

  3DCoat is a commercial digital sculpting program from Pilgway designed to create free-form organic and hard surfaced 3D models, with tools which enable users to sculpt, add polygonal topology (automatically or manually), create UV maps (automatically or manually), texture the resulting models with natural painting tools, and render static images or animated "turntable" movies. The program can also be used to modify imported 3D models from a number of commercial 3D software products by means of plugins called Applinks. Imported models can be converted into voxel objects for further refinement and for adding high resolution detail, complete UV unwrapping and mapping, as well as adding PBR textures for displacement, bump maps, specular and diffuse color maps. A live connection to a chosen external 3D application can be established through the Applink pipeline, allowing for the transfer of model and texture information. 3DCoat specializes in voxel sculpting and polygonal sculpting using dynamic patch tessellation technology and polygonal sculpting tools. It includes "auto-retopology", a proprietary skinning algorithm which generates a polygonal mesh skin over any voxel sculpture, composed primarily of quadrangles.

  Read more →
• 

  Conversica

  Conversica is a US-based cloud software technology company, headquartered in San Mateo, California, that provides two-way AI-driven conversational software and a suite of Intelligent Virtual Assistants for businesses to engage customers via email, chat, and SMS. == History == 2007: The company was founded by Ben Brigham in Bellingham, Washington, originally as AutoFerret.com. The company's initial product was a Customer Relationship Management (CRM) targeted at automotive dealerships. This soon expanded to lead generation, and then lead validation and qualification. The AI Conversica uses currently was made to follow up on and filter out low-quality leads. The focus of the company shifted toward this automated lead engagement technology. 2010: The company started commercially selling AVA, the first Automated Virtual Assistant for sales, and the company name was changed to AVA.ai. Early customers for AVA were automotive dealerships. As the company moved away from generating leads themselves, and providing the CRM themselves, it became necessary to integrate with existing CRM and Marketing Automation platforms, such as DealerSocket, VinSolutions and Salesforce. 2013: The company raised $16m Series A funding, led by Kennet Partners, and named Mark Bradley as CEO. It also moved its headquarters from Bellingham, Washington to Foster City, California. 2014: The company changed its name from AVA.ai to Conversica. 2015: Alex Terry joined Conversica as its CEO. The business expanded to include customers in additional verticals, including technology, education, and financial services. 2016: The company raised $34m Series B funding, led by Providence Strategic Growth. 2017: Conversica expanded its intelligent automation platform and IVAs to support additional communication channels (e-mail and SMS text messaging) and communication languages. Conversica also opened a new technology center in Seattle, Washington to expand its AI and machine learning capabilities. 2018: The company raised $31m Series C funding, led by Providence Strategic Growth. Conversica also acquired Intelligens.ai, providing a regional presence in Latin America with an office in Las Condes, Santiago, Chile. The company launched an AI-powered Admissions Assistant for Higher Education industry. 2019: Conversica was selected by Fast Company magazine as one of the Top 10 Most Innovative AI Companies in the World, and was named Marketo's Technology Partner of the Year. The company officially expanded into the EMEA region with the opening of a London office. As of August 2019, Conversica has over 50 different integrations with third parties. In October Conversica won three awards at the fourth annual Global Annual Achievement Awards for Artificial Intelligence. Also that month, Alex Terry stepped down from his role as CEO and was replaced by Jim Kaskade. 2020: As part of Conversica's response to COVID-19, they optimized the business to become profitable in both 2Q20 and 3Q20, before reinvesting in 4Q20. The company transitioned both international operations in EMEA and LATAM to an indirect model with partners (LeadFabric and Nectia Cloud Solutions respectively), and moved a portion of its US-based employees to near-shore centers in Mexico and Brazil, effectively downsizing the company from 250 to 200. Conversica's reseller partner, Nectia, is a major Latin American affiliate and Chile's number one Salesforce partner, and, as part of the partnership, Nectia devoted capital to a brand new company segment, Predict-IA, dedicated to web-based artificial intelligent solutions. Predict-IA was able to immediately service all LATAM opportunities and clients with Conversica's AI Assistants with end-to-end services (marketing, sales, professional services, customer success, and technical support). Conversica's reseller partner, Leadfabric, has offices in Belgium, Amsterdam, Paris, UK, Taiwan, and Romania. == Technology == Conversica's Revenue Digital Assistants™ are AI assistants who engage with leads, prospects, customers, employees, and other persons of interest (Contacts) in a two-way human-like manner, via email, SMS text, and website chat, in English, French, German, Spanish, Portuguese, and Japanese. The RDAs are built on an Intelligent Automation platform that leverages natural language understanding, natural language processing, natural language generation, deep learning and machine learning. The Assistants are generally deployed alongside sales and marketing, customer success, account management, and higher education admissions teams, as part of an augmented workforce. The Intelligent Automation platform integrates with over 50 external systems, including CRM, Marketing Automation, and other systems of record. A partial list of integration partners includes: Salesforce, Marketo, Oracle, HubSpot, DealerSocket, Reynolds & Reynolds, CDK Global, VinSolutions and many more.

  Read more →
• 

  Google Books Ngram Viewer

  The Google Books Ngram Viewer is an online search engine that charts the frequencies of any set of search strings using a yearly count of n-grams found in printed sources published between 1500 and 2022 in Google's text corpora in English, Chinese (simplified), French, German, Hebrew, Italian, Russian, or Spanish. There are also some specialized English corpora, such as American English, British English, and English Fiction. The program can search for a word or a phrase. The n-grams are matched with the text within the selected corpus, and if found in 40 or more books, are then displayed as a graph. The program supports searches for parts of speech and wildcards. It is routinely used in research. == History == The Ngram Viewer was created by Google software engineers Will Brockman and Jon Orwant , who teamed up with Harvard researchers Jean-Baptiste Michel and Erez Lieberman Aiden. The service was released on December 16, 2010. Before the release, it was difficult to quantify the rate of linguistic change because of the absence of a database that was designed for this purpose, said Steven Pinker, a well-known linguist who was one of the co-authors of the Science paper published on the same day. The Google Books Ngram Viewer was developed in the hope of opening a new window to quantitative research in the humanities field, and the database contained 500 billion words from 5.2 million books publicly available from the very beginning. The intended audience was scholarly, but the Google Books Ngram Viewer made it possible for anyone with a computer to see a graph that represents the diachronic change of the use of words and phrases with ease. Lieberman said in response to The New York Times that the developers aimed to provide even children with the ability to browse cultural trends throughout history. In the Science paper, Lieberman and his collaborators called the method of high-volume data analysis in digitized texts "culturomics". == Usage == Commas delimit user-entered search terms, where each comma-separated term is searched in the database as an n-gram (for example, "nursery school" is a 2-gram or bigram). The Ngram Viewer then returns a plotted line chart. Due to limitations on the size of the Ngram database, only matches found in at least 40 books are indexed. == Limitations == The data sets of the Ngram Viewer have been criticized for their reliance upon inaccurate optical character recognition (OCR) and for including large numbers of incorrectly dated and categorized texts. Because of these errors, and because they are uncontrolled for bias (such as the increasing amount of scientific literature, which causes other terms to appear to decline in popularity), care must be taken in using the corpora to study language or test theories. Furthermore, the data sets may not reflect general linguistic or cultural change and can only hint at such an effect because they do not involve any metadata like date published, author, length, or genre, to avoid any potential copyright infringements. Systemic errors like the confusion of s and f in pre-19th century texts (due to the use of ſ, the long s, which is similar in appearance to f) can cause systemic bias. Although the Google Books team claims that the results are reliable from 1800 onwards, poor OCR and insufficient data mean that frequencies given for languages such as Chinese may only be accurate from 1970 onward, with earlier parts of the corpus showing no results at all for common terms, and data for some years containing more than 50% noise. Guidelines for doing research with data from Google Ngram have been proposed that try to address some of the issues discussed above.

  Read more →
• 

  Saliency map

  In computer vision, a saliency map is an image that highlights either the region on which people's eyes focus first or the most relevant regions for machine learning models. The goal of a saliency map is to reflect the degree of importance of a pixel to the human visual system or an otherwise opaque ML model. For example, in this image, a person first looks at the fort and light clouds, so they should be highlighted on the saliency map. == Application == === Overview === Saliency maps have applications in a variety of different problems. Some general applications: ==== Human eye ==== Image and video compression: The human eye focuses only on a small region of interest in the frame. Therefore, it is not necessary to compress the entire frame with uniform quality. According to the authors, using a salience map reduces the final size of the video with the same visual perception. Image and video quality assessment: The main task for an image or video quality metric is a high correlation with user opinions. Differences in salient regions are given more importance and thus contribute more to the quality score. Image retargeting: It aims at resizing an image by expanding or shrinking the noninformative regions. Therefore, retargeting algorithms rely on the availability of saliency maps that accurately estimate all the salient image details. Object detection and recognition: Instead of applying a computationally complex algorithm to the whole image, we can use it to the most salient regions of an image most likely to contain an object. the primary visual cortex (V1) appears to be responsible for the saliency map, according to the V1 Saliency Hypothesis. ==== Explainable artificial intelligence ==== Saliency maps are a prominent tool in explainable artificial intelligence, providing visual explanations of the decision-making process of machine learning models, particularly deep neural networks. These maps highlight the regions in input data that are most influential on the model's output, effectively indicating where the model is "looking" when making a prediction. In image classification tasks, for example, saliency maps can identify pixels or regions that contribute most to a specific class decision. Developed for convolutional neural networks, saliency mapping techniques range from simply taking the gradient of the class score with respect to the input data to more complex algorithms, such as integrated gradients and class activation mapping. In transformer architecture, attention mechanisms led to analogous saliency maps, such as attention maps, attention rollouts, and class-discriminative attention maps. === Saliency as a segmentation problem === Saliency estimation may be viewed as an instance of image segmentation. In computer vision, image segmentation is the process of partitioning a digital image into multiple segments (sets of pixels, also known as superpixels). The goal of segmentation is to simplify and/or change the representation of an image into something that is more meaningful and easier to analyze. Image segmentation is typically used to locate objects and boundaries (lines, curves, etc.) in images. More precisely, image segmentation is the process of assigning a label to every pixel in an image such that pixels with the same label share certain characteristics. == Algorithms == === Overview === There are three forms of classic saliency estimation algorithms implemented in OpenCV: Static saliency: Relies on image features and statistics to localize the regions of interest of an image. Motion saliency: Relies on motion in a video, detected by optical flow. Objects that move are considered salient. Objectness: Objectness reflects how likely an image window covers an object. These algorithms generate a set of bounding boxes of where an object may lie in an image. In addition to classic approaches, neural-network-based are also popular. There are examples of neural networks for motion saliency estimation: TASED-Net: It consists of two building blocks. First, the encoder network extracts low-resolution spatiotemporal features, and then the following prediction network decodes the spatially encoded features while aggregating all the temporal information. STRA-Net: It emphasizes two essential issues. First, spatiotemporal features integrated via appearance and optical flow coupling, and then multi-scale saliency learned via attention mechanism. STAViS: It combines spatiotemporal visual and auditory information. This approach employs a single network that learns to localize sound sources and to fuse the two saliencies to obtain a final saliency map. There's a new static saliency in the literature with name visual distortion sensitivity. It is based on the idea that the true edges, i.e. object contours, are more salient than the other complex textured regions. It detects edges in a different way from the classic edge detection algorithms. It uses a fairly small threshold for the gradient magnitudes to consider the mere presence of the gradients. So, it obtains 4 binary maps for vertical, horizontal and two diagonal directions. The morphological closing and opening are applied to the binary images to close the small gaps. To clear the blob-like shapes, it utilizes the distance transform. After all, the connected pixel groups are individual edges (or contours). A threshold of size of connected pixel set is used to determine whether an image block contains a perceivable edge (salient region) or not. === Example implementation === First, we should calculate the distance of each pixel to the rest of pixels in the same frame: S A L S ( I k ) = ∑ i = 1 N | I k − I i | {\displaystyle \mathrm {SALS} (I_{k})=\sum _{i=1}^{N}|I_{k}-I_{i}|} I i {\displaystyle I_{i}} is the value of pixel i {\displaystyle i} , in the range of [0,255]. The following equation is the expanded form of this equation. SALS(Ik) = |Ik - I1| + |Ik - I2| + ... + |Ik - IN| Where N is the total number of pixels in the current frame. Then we can further restructure our formula. We put the value that has same I together. SALS(Ik) = Σ Fn × |Ik - In| Where Fn is the frequency of In. And the value of n belongs to [0,255]. The frequencies is expressed in the form of histogram, and the computational time of histogram is ⁠ O ( N ) {\displaystyle O(N)} ⁠ time complexity. ==== Time complexity ==== This saliency map algorithm has ⁠ O ( N ) {\displaystyle O(N)} ⁠ time complexity. Since the computational time of histogram is ⁠ O ( N ) {\displaystyle O(N)} ⁠ time complexity which N is the number of pixel's number of a frame. Besides, the minus part and multiply part of this equation need 256 times operation. Consequently, the time complexity of this algorithm is ⁠ O ( N + 256 ) {\displaystyle O(N+256)} ⁠ which equals to ⁠ O ( N ) {\displaystyle O(N)} ⁠. ==== Pseudocode ==== All of the following code is pseudo MATLAB code. First, read data from video sequences. After we read data, we do superpixel process to each frame. Spnum1 and Spnum2 represent the pixel number of current frame and previous pixel. Then we calculate the color distance of each pixel, this process we call it contract function. After this two process, we will get a saliency map, and then store all of these maps into a new FileFolder. ==== Difference in algorithms ==== The major difference between function one and two is the difference of contract function. If spnum1 and spnum2 both represent the current frame's pixel number, then this contract function is for the first saliency function. If spnum1 is the current frame's pixel number and spnum2 represent the previous frame's pixel number, then this contract function is for second saliency function. If we use the second contract function which using the pixel of the same frame to get center distance to get a saliency map, then we apply this saliency function to each frame and use current frame's saliency map minus previous frame's saliency map to get a new image which is the new saliency result of the third saliency function. == Datasets == The saliency dataset usually contains human eye movements on some image sequences. It is valuable for new saliency algorithm creation or benchmarking the existing one. The most valuable dataset parameters are spatial resolution, size, and eye-tracking equipment. Here is part of the large datasets table from MIT/Tübingen Saliency Benchmark datasets, for example. To collect a saliency dataset, image or video sequences and eye-tracking equipment must be prepared, and observers must be invited. Observers must have normal or corrected to normal vision and must be at the same distance from the screen. At the beginning of each recording session, the eye-tracker recalibrates. To do this, the observer fixates their gaze on the screen center. The session is then started, and saliency data are collected by showing sequences and recording eye gazes. The eye-tracking device is a high-speed camera, capable of recording eye movements at least 250 fr

  Read more →
• 

  Screen space ambient occlusion

  Screen space ambient occlusion (SSAO) is a computer graphics technique for efficiently approximating the ambient occlusion effect in real time. It was developed by Vladimir Kajalin while working at Crytek and was used for the first time in 2007 by the video game Crysis, also developed by Crytek. == Implementation == The algorithm is implemented as a pixel shader, analyzing the scene depth buffer which is stored in a texture. For every pixel on the screen, the pixel shader samples the depth values around the current pixel and tries to compute the amount of occlusion from each of the sampled points. In its simplest implementation, the occlusion factor depends only on the depth difference between sampled point and current point. Without additional smart solutions, such a brute force method would require about 200 texture reads per pixel for good visual quality. This is not acceptable for real-time rendering on current graphics hardware. In order to get high quality results with far fewer reads, sampling is performed using a randomly rotated kernel. The kernel orientation is repeated every N screen pixels in order to have only high-frequency noise in the final picture. In the end this high frequency noise is greatly removed by a NxN post-process blurring step taking into account depth discontinuities (using methods such as comparing adjacent normals and depths). Such a solution allows a reduction in the number of depth samples per pixel to about 16 or fewer while maintaining a high quality result, and allows the use of SSAO in soft real-time applications like computer games. Compared to other ambient occlusion solutions, SSAO has the following advantages: Independent from scene complexity. No data pre-processing needed, no loading time and no memory allocations in system memory. Works with dynamic scenes. Works in the same consistent way for every pixel on the screen. No CPU usage – it can be executed completely on the GPU. May be easily integrated into any modern graphics pipeline. SSAO also has the following disadvantages: Rather local and in many cases view-dependent, as it is dependent on adjacent texel depths which may be generated by any geometry whatsoever. Hard to correctly smooth/blur out the noise without interfering with depth discontinuities, such as object edges (the occlusion should not "bleed" onto objects). Because SSAO operates only on the current depth buffer, it can miss occluding geometry that is not rasterized into the z-buffer and may produce undersampling-related artifacts.

  Read more →
• 

  Backend as a service

  Backend as a service (BaaS), sometimes also referred to as mobile backend as a service (MBaaS), is a service for providing web app and mobile app developers with a way to easily build a backend to their frontend applications. Features available include user management, push notifications, and integration with social networking services. These services are provided via the use of custom software development kits (SDKs) and application programming interfaces (APIs). BaaS is a relatively recent development in cloud computing, with most BaaS startups dating from 2011 or later. Some of the most popular service providers are AWS Amplify and Firebase. == Purpose == Web and mobile apps require a similar set of features on the backend, including notification service, integration with social networks, and cloud storage. Each of these services has its own API that must be individually incorporated into an app, a process that can be time-consuming and complicated for app developers. BaaS providers form a bridge between the frontend of an application and various cloud-based backends via a unified API and SDK. Providing a consistent way to manage backend data means that developers do not need to redevelop their own backend for each of the services that their apps need to access, potentially saving both time and money. Although similar to other cloud-computing business models, such as serverless computing, software as a service (SaaS), infrastructure as a service (IaaS), and platform as a service (PaaS), BaaS is distinct from these other services in that it specifically addresses the cloud-computing needs of web and mobile app developers by providing a unified means of connecting their apps to cloud services. == Features == BaaS providers offer different set of features and backend tools. Some of the most common features include: Database management. Most BaaS solutions provide SQL and/or NoSQL database management services for applications. Developers can store their app data without deploying and managing databases themselves. BaaS usually provides client SDKs, REST and GraphQL APIs for the frontend to interact with databases. File storage. BaaS providers often offer storage solutions for media files, user uploads, and other binary data. Applications can upload, download, and delete files through provided SDKs and APIs. Authentication and authorization. Some BaaS offer authentication and authorization services that allow developers to easily manage app users. This includes user sign-up, login, password reset, social media login integration through OAuth, user group and permission management etc. Notification service. Some BaaS providers such as Firebase and AWS Amplify have notification services that can send custom emails to users and push native notifications on mobile platforms. This is especially useful for applications that need to send messages, alerts, and reminders. Cloud functions. Some BaaS allow developers to deploy and run serverless functions. The functions are usually stateless and can be triggered by various ways including HTTP requests, SDK invocation, background server events, and cloud scheduled executions. Different providers offer runtime support for different languages, some of the popular languages are JavaScript/TypeScript (Node.js, Deno), Python, Java/Kotlin. Cloud functions extend the potential and flexibility of BaaS by allowing developers to write custom functionalities for their apps, working in a way similar to a traditional REST API backend framework. Usage analytics. Analytics data about application usage is often included in BaaS. This allows developers to monitor user behaviors and make decisions correspondingly in marketing strategies and performance optimizations. UI design. Some BaaS providers, such as AWS Amplify and Backendless, offer user interface designing tools that help developers design the frontend UI of web and mobile apps. While this may be useful for small teams and individual developers, UI design assistance may not be conventional in BaaS as it goes beyond the scope of backend infrastructure. Real-Time. Real-time features in a BaaS platform ensure that data updates and synchronizations occur instantly across all clients, making changes immediately visible to users. This is crucial for applications like live chat and collaborative tools, using technologies like WebSockets to maintain continuous server-client connections. == Service providers == BaaS providers have a broad focus, providing SDKs and APIs that work for app development on multiple platforms with different technology stacks, such as JavaScript (for Web apps), Flutter, Java/Kotlin (for Android apps), Swift/Objective-C (for iOS/MacOS/WatchOS/TvOS apps), .NET (for Windows) and others. BaaS providers also come in different types, suiting developers of different needs. === Cloud-based BaaS === Most BaaS providers host backend platforms on their cloud servers. They also manage the infrastructure, security, and scalability of the platforms. Developers can access the backend services via a web interface or the provided APIs. Some examples of cloud-based BaaS include Firebase (hosted on Google Cloud Platform), AWS Amplify (hosted on Amazon Web Services), and Microsoft Azure Mobile Apps (hosted on Microsoft Azure). === Self-hosted BaaS === Self-hosted BaaS allow developers to host backend on their own servers, providing more flexibility and potential to customization compared to cloud-based BaaS, which often is more difficult to migrate from. However, developers are also in charge of managing the infrastructure, security, and scalability of their servers. === Mobile BaaS === Mobile backend as a service (MBaaS) is a type of BaaS specifically for applications deployed in mobile systems. While some references use MBaaS interchangeably for BaaS, BaaS can have a wider variety of support such as for web apps and desktop apps. == Business model == BaaS providers generate revenue from their services in various ways, often using a freemium model. Under this model, a client receives a certain number of free active users or API calls per month, and pays a fee for each user or call over this limit. Alternatively, clients can pay a set fee for a package which allows for a greater number of calls or active users per month. There are also flat fee plans that make the pricing more predictable. Some of the providers offer the unlimited API calls inside their free plan offerings. Another business model that has been used by a lot of BaaS providers is PAYG (pay as you go), which has a flexible cost based on developers' usage of database, storage, bandwidth, function calls, user numbers etc.

  Read more →
• 

  EXAPT

  EXAPT (a portmanteau of "Extended Subset of APT") is a production-oriented programming language that allows users to generate NC programs with control information for machining tools and facilitates decision-making for production-related issues that may arise during various machining processes. EXAPT was first developed to address industrial requirements. Through the years, the company created additional software for the manufacturing industry. Today, EXAPT offers a suite of SAAS products and services for the manufacturing industry. The trade name, EXAPT, is most commonly associated with the CAD/CAM-System, production data, and tool management software of the German company EXAPT Systemtechnik GmbH based in Aachen, DE. == General == EXAPT is a modularly built programming system for all NC machining operations as Drilling Turning Milling Turn-Milling Nibbling Flame-, laser-, plasma- and water jet cutting Wire eroding Operations with industrial robots Due to the modular structure, the main product groups, EXAPTcam and EXAPTpdo, are gradually expandable and permit individual software for the manufacturing industry used individually and also in a compound with an existing IT environment. == Functionality == EXAPTcam meets the requirements for NC planning, especially for the cutting operations such as turning, drilling, and milling up to 5-axis simultaneous machining. Thereby new process technologies, tool, and machine concepts are constantly involved. In the NC programming data from different sources such as 3D CAD models, drawings or tables can flow in. The possibilities of NC programming reaches from language-oriented to feature-oriented NC programming. The integrated EXAPT knowledge database and intelligent and scalable automatisms support the user. The EXAPT NC planning also covers the generation of production information as clamping and tool plans, presetting data or time calculations. The realistic simulation possibilities of NC planning and NC control data provide with production reliability. EXAPTpdo (EXAPT ProductionsDataOrganization) provides a neutrally applicable technology platform for the information compound of the NC planning - to the shop floor. This applies to all NC production data that are necessary for the set-up of NC machines, for the provision, presetting, and stocking of manufacturing resources and provided by EXAPTpdo in a central database. Besides classical functions of the tool management system (TMS) as the management of cutting tools, measuring, testing and clamping devices the technology data management and tool lifecycle management (TLM) is also included. System-supported "where-used lists" helps to handle the manufacturing resource cycle by secured requirement determination and requirement fulfillment. Unnecessary transports and unplanned dispositive adjustments are dropped, stocks are reduced, set-up times reduced and the throughput is increased. EXAPTpdo synchronizes involved systems within the value chain. Stock systems, MES systems or ERP systems (e.g. from the purchasing or production areas) do not work in isolation from each other but they interact with each other. EXAPTpdo provides the base to Smart Factory, for more flexibility in production and faster communication. == History == With the foundation of the EXAPT-Verein in 1967 as spin-off of the universities Aachen, Berlin and Stuttgart the further development "EXAPT (EXtended Subset of APT)" of the programming language "APT (Automatically Programmed Tool)" was focused and so the first milestone for the EXAPT history was set. In the same year the system EXAPT 1 for drilling and simple milling tasks became available. 1969 The industrial application of EXAPT 2 for the programming of NC machines with 2-axis linear and path control begins. In the following year, the development of the EXAPT modular system starts. 1972 BASIC-EXAPT is provided for the universal, homogeneous programming of all NC tasks. The support is made by the EXAPT applications consultancy. 1973 EXAPT 1.1 is provided for the programming of straight-cut and continuous-path controlled drilling and milling machines and machining centers. At the Hanover Fair (IHA 73) the interactive access to a mainframe via a time-sharing terminal for the part program entry and correction is presented and starts the replacement of the punch card. 1974 The possibilities for the use of process computers for the NC data transfer are leveled out. EXAPT offers the possibility of the result simulation when using plotters with display of tool paths and tools in assignment to the workpiece. In April 1975, the EXAPT NC Systemtechnik GmbH was founded with the aim, of enabling entry into the NC technique for small and medium-sized companies by a complete product and service program. In the following year, the system portfolio is extended with further system modules and service programs and the provision of postprocessors. 1978 The development activities on the EXAPT module system started in 1970 are completed. Using modern software techniques, the different system parts BASIC-EXAPT, EXAPT 1, EXAPT 1.1, and EXAPT 2 are composed of a total system. System support and applications consultancy become a new working focus. From the beginning to the middle of the 1980s Beside new portable software modules for CAD/CAM applications (e. g. CAPEX, NESTEX, CADEX, CADCPL), the first version of the EXAPT DNC system and extensions of the EXAPT NC programming system for the machining of sculptured surfaces are presented. 1988 EXAPT expands the software product range by systems for tool data management (BMO) and production data management (FDO). EXAPT trains more than 1,300 course participants including company-specific courses. 1992 The first version of the completely new product generation EXAPTplus is presented and the agency in Dresden is opened. 1993 The company name "EXAPT NC Systemtechnik GmbH" is changed to "EXAPT Systemtechnik GmbH." EXAPTplus is presented on PC under Windows NT at the EMO '93. The decentralization of the use of EXAPT systems expands the range of applications. In the following year, EXAPT-DNC is executable under Windows on a customary PC. Special hardware is not needed and so it can be used in compound with the database-supported EXAPT production data management system (FDO). 1995 EXAPTplus is also ready for complex application cases such as machining of tubes at extrusion tools. EXAPT-CADI provides the transfer of 2D CAD data to EXAPTplus. With the new office Gießen the marketing is strengthened. In the following year the EXAPT NC editor is developed for the direct processing of NC control data with tool path display and visualization of the tools. In the course of the market entry of more comfortable 3D CAD systems for the solid modelling of components a detailed evaluation of current systems is made in 1997. It is decided to use SolidWorks as a reference system for the solid-oriented NC planning with EXAPT. 1998 The first solution for the transfer of geometry data between SolidWorks and EXAPTplus is generated. The EXAPT organization systems are (beside SQL) also executable under Oracle now. The use of client server solutions supports the data flow in the production. 1999 AFR functions are provided in connection with EXAPTsolid to support a workpiece modelling for NC. The millennium capability is ensured for all EXAPT systems. AFR is a ground-breaking for the integration of third-party products. 2002 EXAPT-BMG is developed for the generation and visualization of tools with additional functions for the assembly from components. The acquisition of tools with their geometric and technological presentation offers extensive support of the NC planning with EXAPT systems. 2003 EXAPTpdo is available to optimize the process chains in production planning and production execution optimally regarding the increasing requirements of changing production conditions. 2004 Diverse system extensions are made in EXAPTplus, EXAPTsolid, EXAPT NC editor, EXAPTpdo for the complete machining on turning/milling centres with result reliability because of more extensive simulation based on realNC (Tecnomatix), for the use of new complex tool systems and the compound use between ERP systems as SAP and intelligent CNC systems. In the following year, EXAPTpdo is extended for the cross-order set-up optimization and provision of manufacturing re-sources especially for single and small series production with connection to purchase and physical portfolio management. 2006 The EXAPT systems are available for extended use as an information platform for production, the time management, and similar requirements. EXAPTsolid is extended for the feature-oriented milling operation and machine simulation. The NC programming of complex machine tools, e.g. three-turret-turning/milling centers is supported by EXAPT systems, as well as the use of multi-functional tools. 2007 A module for 3-5-axis simultaneous milling machining is presented.

  Read more →
• 

  Convolutional layer

  In artificial neural networks, a convolutional layer is a type of network layer that applies a convolution operation to the input. Convolutional layers are some of the primary building blocks of convolutional neural networks (CNNs), a class of neural network most commonly applied to images, video, audio, and other data that have the property of uniform translational symmetry. The convolution operation in a convolutional layer involves sliding a small window (called a kernel or filter) across the input data and computing the dot product between the values in the kernel and the input at each position. This process creates a feature map that represents detected features in the input. == Concepts == === Kernel === Kernels, also known as filters, are small matrices of weights that are learned during the training process. Each kernel is responsible for detecting a specific feature in the input data. The size of the kernel is a hyperparameter that affects the network's behavior. === Convolution === For a 2D input x {\displaystyle x} and a 2D kernel w {\displaystyle w} , the 2D convolution operation can be expressed as: y [ i , j ] = ∑ m = 0 k h − 1 ∑ n = 0 k w − 1 x [ i + m , j + n ] ⋅ w [ m , n ] {\displaystyle y[i,j]=\sum _{m=0}^{k_{h}-1}\sum _{n=0}^{k_{w}-1}x[i+m,j+n]\cdot w[m,n]} where k h {\displaystyle k_{h}} and k w {\displaystyle k_{w}} are the height and width of the kernel, respectively. This generalizes immediately to nD convolutions. Commonly used convolutions are 1D (for audio and text), 2D (for images), and 3D (for spatial objects, and videos). === Stride === Stride determines how the kernel moves across the input data. A stride of 1 means the kernel shifts by one pixel at a time, while a larger stride (e.g., 2 or 3) results in less overlap between convolutions and produces smaller output feature maps. === Padding === Padding involves adding extra pixels around the edges of the input data. It serves two main purposes: Preserving spatial dimensions: Without padding, each convolution reduces the size of the feature map. Handling border pixels: Padding ensures that border pixels are given equal importance in the convolution process. Common padding strategies include: No padding/valid padding. This strategy typically causes the output to shrink. Same padding: Any method that ensures the output size same as input size is a same padding strategy. Full padding: Any method that ensures each input entry is convolved over for the same number of times is a full padding strategy. Common padding algorithms include: Zero padding: Add zero entries to the borders of input. Mirror/reflect/symmetric padding: Reflect the input array on the border. Circular padding: Cycle the input array back to the opposite border, like a torus. The exact numbers used in convolutions is complicated, for which we refer to (Dumoulin and Visin, 2018) for details. == Variants == === Standard === The basic form of convolution as described above, where each kernel is applied to the entire input volume. === Depthwise separable === Depthwise separable convolution separates the standard convolution into two steps: depthwise convolution and pointwise convolution. The depthwise separable convolution decomposes a single standard convolution into two convolutions: a depthwise convolution that filters each input channel independently and a pointwise convolution ( 1 × 1 {\displaystyle 1\times 1} convolution) that combines the outputs of the depthwise convolution. This factorization significantly reduces computational cost. It was first developed by Laurent Sifre during an internship at Google Brain in 2013 as an architectural variation on AlexNet to improve convergence speed and model size. === Dilated === Dilated convolution, or atrous convolution, introduces gaps between kernel elements, allowing the network to capture a larger receptive field without increasing the kernel size. === Transposed === Transposed convolution, also known as deconvolution, fractionally strided convolution, and upsampling convolution, is a convolution where the output tensor is larger than its input tensor. It's often used in encoder-decoder architectures for upsampling. It's used in image generation, semantic segmentation, and super-resolution tasks. == History == The concept of convolution in neural networks was inspired by the visual cortex in biological brains. Early work by Hubel and Wiesel in the 1960s on the cat's visual system laid the groundwork for artificial convolution networks. An early convolution neural network was developed by Kunihiko Fukushima in 1969. It had mostly hand-designed kernels inspired by convolutions in mammalian vision. In 1979 he improved it to the Neocognitron, which learns all convolutional kernels by unsupervised learning (in his terminology, "self-organized by 'learning without a teacher'"). During the 1988 to 1998 period, a series of CNN were introduced by Yann LeCun et al., ending with LeNet-5 in 1998. It was an early influential CNN architecture for handwritten digit recognition, trained on the MNIST dataset, and was used in ATM. (Olshausen & Field, 1996) discovered that simple cells in the mammalian primary visual cortex implement localized, oriented, bandpass receptive fields, which could be recreated by fitting sparse linear codes for natural scenes. This was later found to also occur in the lowest-level kernels of trained CNNs. The field saw a resurgence in the 2010s with the development of deeper architectures and the availability of large datasets and powerful GPUs. AlexNet, developed by Alex Krizhevsky et al. in 2012, was a catalytic event in modern deep learning. In that year’s ImageNet competition, the AlexNet model achieved a 16% top-five error rate, significantly outperforming the next best entry, which had a 26% error rate. The network used eight trainable layers, approximately 650,000 neurons, and around 60 million parameters, highlighting the impact of deeper architectures and GPU acceleration on image recognition performance. From the 2013 ImageNet competition, most entries adopted deep convolutional neural networks, building on the success of AlexNet. Over the following years, performance steadily improved, with the top-five error rate falling from 16% in 2012 and 12% in 2013 to below 3% by 2017, as networks grew increasingly deep.

  Read more →
• 

  Cross-validation (statistics)

  Cross-validation, sometimes called rotation estimation or out-of-sample testing, is any of various similar model validation techniques for assessing how the results of a statistical analysis will generalize to an independent data set. Cross-validation includes resampling and sample splitting methods that use different portions of the data to test and train a model on different iterations. It is often used in settings where the goal is prediction, and one wants to estimate how accurately a predictive model will perform in practice. It can also be used to assess the quality of a fitted model and the stability of its parameters. In a prediction problem, a model is usually given a dataset of known data on which training is run (training dataset), and a dataset of unknown data (or first seen data) against which the model is tested (called the validation dataset or testing set). The goal of cross-validation is to test the model's ability to predict new data that was not used in estimating it, in order to flag problems like overfitting or selection bias and to give an insight on how the model will generalize to an independent dataset (i.e., an unknown dataset, for instance from a real problem). One round of cross-validation involves partitioning a sample of data into complementary subsets, performing the analysis on one subset (called the training set), and validating the analysis on the other subset (called the validation set or testing set). To reduce variability, in most methods multiple rounds of cross-validation are performed using different partitions, and the validation results are combined (e.g. averaged) over the rounds to give an estimate of the model's predictive performance. In summary, cross-validation combines (averages) measures of fitness in prediction to derive a more accurate estimate of model prediction performance. == Motivation == Assume a model with one or more unknown parameters, and a data set to which the model can be fit (the training data set). The fitting process optimizes the model parameters to make the model fit the training data as well as possible. If an independent sample of validation data is taken from the same population as the training data, it will generally turn out that the model does not fit the validation data as well as it fits the training data. The size of this difference is likely to be large especially when the size of the training data set is small, or when the number of parameters in the model is large. Cross-validation is a way to estimate the size of this effect. === Example: linear regression === In linear regression, there exist real response values y 1 , … , y n {\textstyle y_{1},\ldots ,y_{n}} , and n p-dimensional vector covariates x1, ..., xn. The components of the vector xi are denoted xi1, ..., xip. If least squares is used to fit a function in the form of a hyperplane ŷ = a + βTx to the data (xi, yi) 1 ≤ i ≤ n, then the fit can be assessed using the mean squared error (MSE). The MSE for given estimated parameter values a and β on the training set (xi, yi) 1 ≤ i ≤ n is defined as: MSE = 1 n ∑ i = 1 n ( y i − y ^ i ) 2 = 1 n ∑ i = 1 n ( y i − a − β T x i ) 2 = 1 n ∑ i = 1 n ( y i − a − β 1 x i 1 − ⋯ − β p x i p ) 2 {\displaystyle {\begin{aligned}{\text{MSE}}&={\frac {1}{n}}\sum _{i=1}^{n}(y_{i}-{\hat {y}}_{i})^{2}={\frac {1}{n}}\sum _{i=1}^{n}(y_{i}-a-{\boldsymbol {\beta }}^{T}\mathbf {x} _{i})^{2}\\&={\frac {1}{n}}\sum _{i=1}^{n}(y_{i}-a-\beta _{1}x_{i1}-\dots -\beta _{p}x_{ip})^{2}\end{aligned}}} If the model is correctly specified, it can be shown under mild assumptions that the expected value of the MSE for the training set is (n − p − 1)/(n + p + 1) < 1 times the expected value of the MSE for the validation set (the expected value is taken over the distribution of training sets). Thus, a fitted model and computed MSE on the training set will result in an optimistically biased assessment of how well the model will fit an independent data set. This biased estimate is called the in-sample estimate of the fit, whereas the cross-validation estimate is an out-of-sample estimate. Since in linear regression it is possible to directly compute the factor (n − p − 1)/(n + p + 1) by which the training MSE underestimates the validation MSE under the assumption that the model specification is valid, cross-validation can be used for checking whether the model has been overfitted, in which case the MSE in the validation set will substantially exceed its anticipated value. (Cross-validation in the context of linear regression is also useful in that it can be used to select an optimally regularized cost function.) === General case === In most other regression procedures (e.g. logistic regression), there is no simple formula to compute the expected out-of-sample fit. Cross-validation is, thus, a generally applicable way to predict the performance of a model on unavailable data using numerical computation in place of theoretical analysis. == Types == Two types of cross-validation can be distinguished: exhaustive and non-exhaustive cross-validation. === Exhaustive cross-validation === Exhaustive cross-validation methods are cross-validation methods which learn and test on all possible ways to divide the original sample into a training and a validation set. ==== Leave-p-out cross-validation ==== Leave-p-out cross-validation (LpO CV) involves using p observations as the validation set and the remaining observations as the training set. This is repeated on all ways to cut the original sample on a validation set of p observations and a training set. LpO cross-validation require training and validating the model C p n {\displaystyle C_{p}^{n}} times, where n is the number of observations in the original sample, and where C p n {\displaystyle C_{p}^{n}} is the binomial coefficient. For p > 1 and for even moderately large n, LpO CV can become computationally infeasible. For example, with n = 100 and p = 30, C 30 100 ≈ 3 × 10 25 . {\displaystyle C_{30}^{100}\approx 3\times 10^{25}.} A variant of LpO cross-validation with p=2 known as leave-pair-out cross-validation has been recommended as a nearly unbiased method for estimating the area under ROC curve of binary classifiers. ==== Leave-one-out cross-validation ==== Leave-one-out cross-validation (LOOCV) is a particular case of leave-p-out cross-validation with p = 1. The process looks similar to jackknife; however, with cross-validation one computes a statistic on the left-out sample(s), while with jackknifing one computes a statistic from the kept samples only. LOO cross-validation requires less computation time than LpO cross-validation because there are only C 1 n = n {\displaystyle C_{1}^{n}=n} passes rather than C p n {\displaystyle C_{p}^{n}} . However, n {\displaystyle n} passes may still require quite a large computation time, in which case other approaches such as k-fold cross validation may be more appropriate. Pseudo-code algorithm: Input: x, {vector of length N with x-values of incoming points} y, {vector of length N with y-values of the expected result} interpolate( x_in, y_in, x_out ), { returns the estimation for point x_out after the model is trained with x_in-y_in pairs} Output: err, {estimate for the prediction error} Steps: err ← 0 for i ← 1, ..., N do // define the cross-validation subsets x_in ← (x[1], ..., x[i − 1], x[i + 1], ..., x[N]) y_in ← (y[1], ..., y[i − 1], y[i + 1], ..., y[N]) x_out ← x[i] y_out ← interpolate(x_in, y_in, x_out) err ← err + (y[i] − y_out)^2 end for err ← err/N === Non-exhaustive cross-validation === Non-exhaustive cross validation methods do not compute all ways of splitting the original sample. These methods are approximations of leave-p-out cross-validation. ==== k-fold cross-validation ==== In k-fold cross-validation, the original sample is randomly partitioned into k equal sized subsamples, often referred to as "folds". Of the k subsamples, a single subsample is retained as the validation data for testing the model, and the remaining k − 1 subsamples are used as training data. The cross-validation process is then repeated k times, with each of the k subsamples used exactly once as the validation data. The k results can then be averaged to produce a single estimation. The advantage of this method over repeated random sub-sampling (see below) is that all observations are used for both training and validation, and each observation is used for validation exactly once. 10-fold cross-validation is commonly used, but in general k remains an unfixed parameter. For example, setting k = 2 results in 2-fold cross-validation. In 2-fold cross-validation, the dataset is randomly shuffled into two sets d0 and d1, so that both sets are equal size (this is usually implemented by shuffling the data array and then splitting it in two). We then train on d0 and validate on d1, followed by training on d1 and validating on d0. When k = n (the number of observations), k-fold cross-validation is equivalent to leave-one-out cr

  Read more →
• 

  FloodAlerts

  FloodAlerts is a software application, developed by software specialists Shoothill, which takes real-time flooding information, and displays the data on an interactive Bing map, updating and warning its users when they, their premises or the routes they need to travel could be at risk of flooding. == History == FloodAlerts was launched in 2012, originally as the world's first Facebook flood warning app. == Operation == FloodAlerts is made available free of charge to individuals. Users are able to set up their own monitored locations and receive alerts via the application or their Facebook wall if the locations they are monitoring are at imminent risk of flooding. Hosted in the Cloud, using the Microsoft Windows Azure platform, the FloodAlerts application processes the data received from the Environment Agency, automatically creates the required map tiles, pins and alerts and displays them on an interactive Bing map, updating the content every 15 minutes. Users are able to see the latest information on the map without having to refresh their browser. FloodAlerts can also be provided as a customised risk management solution to businesses that require infrastructure or asset safety monitoring in areas where water levels are rising or receding. == Awards and recognition == FloodAlerts has received The Guardian and Virgin Media Business's 2012 Innovation Nation Awards and was shortlisted as a finalist for a further two national awards: the UK IT Industry Awards for Innovation and Entrepreneurship and The Institution of Engineering and Technology Innovation Awards for Information Technology. == In the press == The FloodAlerts application was reviewed on the BBC website. It was also reviewed on BBC Click.

  Read more →
• 

  Latent semantic analysis

  Latent semantic analysis (LSA) is a technique in natural language processing, in particular distributional semantics, of analyzing relationships between a set of documents and the terms they contain by producing a set of concepts related to the documents and terms. LSA assumes that words that are close in meaning will occur in similar pieces of text (the distributional hypothesis). A matrix containing word counts per document (rows represent unique words and columns represent each document) is constructed from a large piece of text and a mathematical technique called singular value decomposition (SVD) is used to reduce the number of rows while preserving the similarity structure among columns. Documents are then compared by cosine similarity between any two columns. Values close to 1 represent very similar documents while values close to 0 represent very dissimilar documents. An information retrieval technique using latent semantic structure was patented in 1988 by Scott Deerwester, Susan Dumais, George Furnas, Richard Harshman, Thomas Landauer, Karen Lochbaum and Lynn Streeter. In the context of its application to information retrieval, it is sometimes called latent semantic indexing (LSI). == Overview == === Occurrence matrix === LSA can use a document-term matrix which describes the occurrences of terms in documents; it is a sparse matrix whose rows correspond to terms and whose columns correspond to documents. A typical example of the weighting of the elements of the matrix is tf-idf (term frequency–inverse document frequency): the weight of an element of the matrix is proportional to the number of times the terms appear in each document, where rare terms are upweighted to reflect their relative importance. This matrix is also common to standard semantic models, though it is not necessarily explicitly expressed as a matrix, since the mathematical properties of matrices are not always used. === Rank lowering === After the construction of the occurrence matrix, LSA finds a low-rank approximation to the term-document matrix. There could be various reasons for these approximations: The original term-document matrix is presumed too large for the computing resources; in this case, the approximated low rank matrix is interpreted as an approximation (a "least and necessary evil"). The original term-document matrix is presumed noisy: for example, anecdotal instances of terms are to be eliminated. From this point of view, the approximated matrix is interpreted as a de-noisified matrix (a better matrix than the original). The original term-document matrix is presumed overly sparse relative to the "true" term-document matrix. That is, the original matrix lists only the words actually in each document, whereas we might be interested in all words related to each document—generally a much larger set due to synonymy. The consequence of the rank lowering is that some dimensions are combined and depend on more than one term: {(car), (truck), (flower)} → {(1.3452 car + 0.2828 truck), (flower)} This mitigates the problem of identifying synonymy, as the rank lowering is expected to merge the dimensions associated with terms that have similar meanings. It also partially mitigates the problem with polysemy, since components of polysemous words that point in the "right" direction are added to the components of words that share a similar meaning. Conversely, components that point in other directions tend to either simply cancel out, or, at worst, to be smaller than components in the directions corresponding to the intended sense. === Derivation === Let X {\displaystyle X} be a matrix where element ( i , j ) {\displaystyle (i,j)} describes the occurrence of term i {\displaystyle i} in document j {\displaystyle j} (this can be, for example, the frequency). X {\displaystyle X} will look like this: d j ↓ t i T → [ x 1 , 1 … x 1 , j … x 1 , n ⋮ ⋱ ⋮ ⋱ ⋮ x i , 1 … x i , j … x i , n ⋮ ⋱ ⋮ ⋱ ⋮ x m , 1 … x m , j … x m , n ] {\displaystyle {\begin{matrix}&{\textbf {d}}_{j}\\&\downarrow \\{\textbf {t}}_{i}^{T}\rightarrow &{\begin{bmatrix}x_{1,1}&\dots &x_{1,j}&\dots &x_{1,n}\\\vdots &\ddots &\vdots &\ddots &\vdots \\x_{i,1}&\dots &x_{i,j}&\dots &x_{i,n}\\\vdots &\ddots &\vdots &\ddots &\vdots \\x_{m,1}&\dots &x_{m,j}&\dots &x_{m,n}\\\end{bmatrix}}\end{matrix}}} Now a row in this matrix will be a vector corresponding to a term, giving its relation to each document: t i T = [ x i , 1 … x i , j … x i , n ] {\displaystyle {\textbf {t}}_{i}^{T}={\begin{bmatrix}x_{i,1}&\dots &x_{i,j}&\dots &x_{i,n}\end{bmatrix}}} Likewise, a column in this matrix will be a vector corresponding to a document, giving its relation to each term: d j = [ x 1 , j ⋮ x i , j ⋮ x m , j ] {\displaystyle {\textbf {d}}_{j}={\begin{bmatrix}x_{1,j}\\\vdots \\x_{i,j}\\\vdots \\x_{m,j}\\\end{bmatrix}}} Now the dot product t i T t p {\displaystyle {\textbf {t}}_{i}^{T}{\textbf {t}}_{p}} between two term vectors gives the correlation between the terms over the set of documents. The matrix product X X T {\displaystyle XX^{T}} contains all these dot products. Element ( i , p ) {\displaystyle (i,p)} (which is equal to element ( p , i ) {\displaystyle (p,i)} ) contains the dot product t i T t p {\displaystyle {\textbf {t}}_{i}^{T}{\textbf {t}}_{p}} ( = t p T t i {\displaystyle ={\textbf {t}}_{p}^{T}{\textbf {t}}_{i}} ). Likewise, the matrix X T X {\displaystyle X^{T}X} contains the dot products between all the document vectors, giving their correlation over the terms: d j T d q = d q T d j {\displaystyle {\textbf {d}}_{j}^{T}{\textbf {d}}_{q}={\textbf {d}}_{q}^{T}{\textbf {d}}_{j}} . Now, from the theory of linear algebra, there exists a decomposition of X {\displaystyle X} such that U {\displaystyle U} and V {\displaystyle V} are orthogonal matrices and Σ {\displaystyle \Sigma } is a diagonal matrix. This is called a singular value decomposition (SVD): X = U Σ V T {\displaystyle {\begin{matrix}X=U\Sigma V^{T}\end{matrix}}} The matrix products giving us the term and document correlations then become X X T = ( U Σ V T ) ( U Σ V T ) T = ( U Σ V T ) ( V T T Σ T U T ) = U Σ V T V Σ T U T = U Σ Σ T U T X T X = ( U Σ V T ) T ( U Σ V T ) = ( V T T Σ T U T ) ( U Σ V T ) = V Σ T U T U Σ V T = V Σ T Σ V T {\displaystyle {\begin{matrix}XX^{T}&=&(U\Sigma V^{T})(U\Sigma V^{T})^{T}=(U\Sigma V^{T})(V^{T^{T}}\Sigma ^{T}U^{T})=U\Sigma V^{T}V\Sigma ^{T}U^{T}=U\Sigma \Sigma ^{T}U^{T}\\X^{T}X&=&(U\Sigma V^{T})^{T}(U\Sigma V^{T})=(V^{T^{T}}\Sigma ^{T}U^{T})(U\Sigma V^{T})=V\Sigma ^{T}U^{T}U\Sigma V^{T}=V\Sigma ^{T}\Sigma V^{T}\end{matrix}}} Since Σ Σ T {\displaystyle \Sigma \Sigma ^{T}} and Σ T Σ {\displaystyle \Sigma ^{T}\Sigma } are diagonal we see that U {\displaystyle U} must contain the eigenvectors of X X T {\displaystyle XX^{T}} , while V {\displaystyle V} must be the eigenvectors of X T X {\displaystyle X^{T}X} . Both products have the same non-zero eigenvalues, given by the non-zero entries of Σ Σ T {\displaystyle \Sigma \Sigma ^{T}} , or equally, by the non-zero entries of Σ T Σ {\displaystyle \Sigma ^{T}\Sigma } . Now the decomposition looks like this: X U Σ V T ( d j ) ( d ^ j ) ↓ ↓ ( t i T ) → [ x 1 , 1 … x 1 , j … x 1 , n ⋮ ⋱ ⋮ ⋱ ⋮ x i , 1 … x i , j … x i , n ⋮ ⋱ ⋮ ⋱ ⋮ x m , 1 … x m , j … x m , n ] = ( t ^ i T ) → [ [ u 1 ] … [ u l ] ] ⋅ [ σ 1 … 0 ⋮ ⋱ ⋮ 0 … σ l ] ⋅ [ [ v 1 ] ⋮ [ v l ] ] {\displaystyle {\begin{matrix}&X&&&U&&\Sigma &&V^{T}\\&({\textbf {d}}_{j})&&&&&&&({\hat {\textbf {d}}}_{j})\\&\downarrow &&&&&&&\downarrow \\({\textbf {t}}_{i}^{T})\rightarrow &{\begin{bmatrix}x_{1,1}&\dots &x_{1,j}&\dots &x_{1,n}\\\vdots &\ddots &\vdots &\ddots &\vdots \\x_{i,1}&\dots &x_{i,j}&\dots &x_{i,n}\\\vdots &\ddots &\vdots &\ddots &\vdots \\x_{m,1}&\dots &x_{m,j}&\dots &x_{m,n}\\\end{bmatrix}}&=&({\hat {\textbf {t}}}_{i}^{T})\rightarrow &{\begin{bmatrix}{\begin{bmatrix}\,\\\,\\{\textbf {u}}_{1}\\\,\\\,\end{bmatrix}}\dots {\begin{bmatrix}\,\\\,\\{\textbf {u}}_{l}\\\,\\\,\end{bmatrix}}\end{bmatrix}}&\cdot &{\begin{bmatrix}\sigma _{1}&\dots &0\\\vdots &\ddots &\vdots \\0&\dots &\sigma _{l}\\\end{bmatrix}}&\cdot &{\begin{bmatrix}{\begin{bmatrix}&&{\textbf {v}}_{1}&&\end{bmatrix}}\\\vdots \\{\begin{bmatrix}&&{\textbf {v}}_{l}&&\end{bmatrix}}\end{bmatrix}}\end{matrix}}} The values σ 1 , … , σ l {\displaystyle \sigma _{1},\dots ,\sigma _{l}} are called the singular values, and u 1 , … , u l {\displaystyle u_{1},\dots ,u_{l}} and v 1 , … , v l {\displaystyle v_{1},\dots ,v_{l}} the left and right singular vectors. Notice the only part of U {\displaystyle U} that contributes to t i {\displaystyle {\textbf {t}}_{i}} is the i 'th {\displaystyle i{\textrm {'th}}} row. Let this row vector be called t ^ i T {\displaystyle {\hat {\textrm {t}}}_{i}^{T}} . Likewise, the only part of V T {\displaystyle V^{T}} that contributes to d j {\displaystyle {\textbf {d}}_{j}} is the j 'th {\displaystyle j{\textrm {'th}}} column, d ^ j {\displaystyle {\hat {\textrm {d}}}_{j}} . These are not the eigenvectors, but depend on all the eigenvectors. I

  Read more →