AI Chat You

AI Chat You — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

WhatsApp

WhatsApp Messenger, commonly known simply as WhatsApp, is an American social media, instant messaging (IM), and Voice over IP (VoIP) service accessible via desktop and mobile app. Owned by Meta Platforms, the service allows users to send text messages, voice messages, and video messages, make voice and video calls, and share images, documents, user locations, and other content. The service requires a cellular mobile telephone number to register. WhatsApp was launched in May 2009. In January 2018, WhatsApp released a standalone business app called WhatsApp Business which can communicate with the standard WhatsApp client. As of May 2025, the service had 3 billion monthly active users, making it the most used messenger app. The name of the app is meant to sound like "what's up". The service was created by WhatsApp Inc. of Mountain View, California, which was acquired by Facebook in February 2014 for approximately US$19.3 billion. It became the world's most popular messaging application in 2015, with 900 million users, and had more than 2 billion active users worldwide in February 2020. WhatsApp Business had approximately 200 million monthly users in 2023. By 2016, it had become the primary means of Internet communication in regions including the Americas, the Indian subcontinent, and large parts of Europe and Africa. == History == === 2009–2014 === WhatsApp was founded by Brian Acton and Jan Koum, former employees of Yahoo. Koum incorporated WhatsApp Inc. in California on February 24, 2009. A month earlier, Koum had purchased an iPhone, and he and Acton decided to create an app for the App Store. The idea started off as an app that would display statuses in a phone's Contacts menu, showing if a person was at work or on a call. Their discussions often took place at the home of Koum's Russian friend Alex Fishman in West San Jose. They realized that to take the idea further, they would need an iPhone developer. Fishman visited RentACoder.com, found Russian developer Igor Solomennikov, and introduced him to Koum. Koum named the app WhatsApp to sound like "what's up" and it was published on the Apple App Store and BlackBerry App World in May and June 2009 respectively. However, when early versions of WhatsApp kept crashing, Koum considered giving up and looking for a new job. Acton encouraged him to wait for a "few more months". In June 2009, when the app had been downloaded by only a handful of Fishman's Russian-speaking friends, Apple launched push technology, allowing users to be pinged even when not using the app. Koum updated WhatsApp so that everyone in the user's network would be notified when a user's status changed. This new facility, to Koum's surprise, was used by users to ping "each other with jokey custom statuses like, 'I woke up late' or 'I'm on my way.'" Fishman said, "At some point it sort of became instant messaging". WhatsApp 2.0, released for iPhone in August 2009, featured a purpose-designed messaging component; the number of active users suddenly increased to 250,000. Although Acton was working on another startup idea, he decided to join the company. In October 2009, Acton persuaded five former friends at Yahoo! to invest $250,000 in seed funding, and Acton became a co-founder and was given a stake. He officially joined WhatsApp on November 1. Koum then hired a friend in Los Angeles, Chris Peiffer, to develop a BlackBerry version, which arrived two months later. Subsequently, WhatsApp for Symbian OS was added in May 2010, and for Android OS in August 2010. In 2010 Google made multiple acquisition offers for WhatsApp, which were all declined. To cover the cost of sending verification texts to users, WhatsApp was changed from a free service to a paid one. In December 2009, the ability to send photos was added to the iOS version. By early 2011, WhatsApp was one of the top 20 apps in the U.S. Apple App Store. In April 2011, Sequoia Capital invested about $8 million for more than 15% of the company, after months of negotiation by Sequoia partner Jim Goetz. By February 2013, WhatsApp had about 200 million active users and 50 staff members. Sequoia invested another $50 million at a $1.5 billion valuation. Some time in 2013 WhatsApp acquired Santa Clara–based startup SkyMobius, the developers of Vtok, a video and voice calling app. As of December 2013, the service had 400 million monthly active users. That year, the company had $148 million in expenses and a net loss of $138 million. === 2014–2015 === On February 19, 2014, one year after the venture capital financing round at a $1.5 billion valuation, Facebook, Inc. (now Meta Platforms) agreed to acquire the company for US$19 billion, its largest acquisition to date. At the time, it was the largest acquisition of a venture-capital-backed company in history. Sequoia Capital received an approximate 5,000% return on its initial investment. Facebook paid $4 billion in cash, $12 billion in Facebook shares, and an additional $3 billion in restricted stock units granted to WhatsApp's founders Koum and Acton. Employee stock was scheduled to vest over four years subsequent to closing. Days after the announcement, WhatsApp users experienced a loss of service, leading to anger across social media. The acquisition was influenced by the data provided by Onavo, Facebook's research app for monitoring competitors and trending usage of social activities on mobile phones, as well as startups that were performing "unusually well". The acquisition caused many users to try, or move to, other message services. Telegram claimed that it acquired 8 million new users, and Line, 2 million. At a keynote presentation at the Mobile World Congress in Barcelona in February 2014, Facebook CEO Mark Zuckerberg said that Facebook's acquisition of WhatsApp was closely related to the Internet.org vision. A TechCrunch article said about Zuckerberg's vision:The idea, he said, is to develop a group of basic internet services that would be free of charge to use – "a 911 for the internet". These could be a social networking service like Facebook, a messaging service, maybe search and other things like weather. Providing a bundle of these free of charge to users will work like a gateway drug of sorts – users who may be able to afford data services and phones these days just don't see the point of why they would pay for those data services. This would give them some context for why they are important, and that will lead them to pay for more services like this – or so the hope goes. Three days after announcing the Facebook purchase, Koum said they were working to introduce voice calls. He also said that new mobile phones would be sold in Germany with the WhatsApp brand, and that their ultimate goal was to be on all smartphones. In August 2014, WhatsApp was the most popular messaging app in the world, with more than 600 million users. By early January 2015, WhatsApp had 700 million monthly users and over 30 billion messages every day. In April 2015, Forbes predicted that between 2012 and 2018, the telecommunications industry would lose $386 billion because of "over-the-top" services like WhatsApp and Skype. That month, WhatsApp had over 800 million users. By September 2015, it had grown to 900 million; and by February 2016, one billion. On November 30, 2015, the Android WhatsApp client made links to Telegram unclickable and not copyable. Multiple sources confirmed that it was intentional, not a bug, and that it had been implemented when the Android source code that recognized Telegram URLs had been identified. (The word "telegram" appeared in WhatsApp's code.) Some considered it an anti-competitive measure; WhatsApp offered no explanation. === 2016–2019 === On January 18, 2016, WhatsApp's co-founder Jan Koum announced that it would no longer charge users a $1 annual subscription fee, in an effort to remove a barrier faced by users without payment cards. He also said that the app would not display any third-party ads, and that it would have new features such as the ability to communicate with businesses. On May 18, 2017, the European Commission announced that it was fining Facebook €110 million for "providing misleading information about WhatsApp takeover" in 2014. The Commission said that in 2014 when Facebook acquired the messaging app, it "falsely claimed it was technically impossible to automatically combine user information from Facebook and WhatsApp." However, in the summer of 2016, WhatsApp had begun sharing user information with its parent company, allowing information such as phone numbers to be used for targeted Facebook advertisements. Facebook acknowledged the breach, but said the errors in their 2014 filings were "not intentional". In September 2017, WhatsApp's co-founder Brian Acton left the company to start a nonprofit group, later revealed as the Signal Foundation, which developed the WhatsApp competitor Signal. He explained his reasons for leaving in an interview with Forbes a year later. WhatsApp also
Read more →
Brave Leo

Brave Leo is a large language model-based chatbot developed by Brave Software and included with the Brave browser. == History == In November 2023, the company said versions for iOS and Android would be available "in the coming months". == Features == Since January 2024, Leo has used the open-source Mixtral 8x7B from Mistral AI as its default large language model, in addition to LLaMA 2 from Meta Platforms and Claude from Anthropic, both of which have been used previously. Leo can suggest follow-up questions, and summarize webpages, PDFs, and videos. Leo has a $15 (US) per month premium version that enables more requests and uses larger LLMs. == Privacy == The answers given by Leo are not saved. Brave uses the slogan Love Privacy to emphasize its focus on user privacy and data protection. The phrase has been featured in Brave's official marketing campaigns and has been cited in media coverage of the browser's privacy-first approach. == Controversies == In 2023, PC World reported that Leo evades questions about US elections.
Read more →
Visual descriptor

In computer vision, visual descriptors or image descriptors are descriptions of the visual features of the contents in images, videos, or algorithms or applications that produce such descriptions. They describe elementary characteristics such as the shape, the color, the texture or the motion, among others. == Introduction == As a result of the new communication technologies and the massive use of Internet in our society, the amount of audio-visual information available in digital format is increasing considerably. Therefore, it has been necessary to design some systems that allow us to describe the content of several types of multimedia information in order to search and classify them. The audio-visual descriptors are in charge of the contents description. These descriptors have a good knowledge of the objects and events found in a video, image or audio and they allow the quick and efficient searches of the audio-visual content. This system can be compared to the search engines for textual contents. Although it is relatively easy to find text with a computer, it is much more difficult to find concrete audio and video parts. For instance, imagine somebody searching a scene of a happy person. The happiness is a feeling and it is not evident its shape, color and texture description in images. The description of the audio-visual content is not a superficial task and it is essential for the effective use of this type of archives. The standardization system that deals with audio-visual descriptors is the MPEG-7 (Motion Picture Expert Group - 7). == Types == Descriptors are the first step to find out the connection between pixels contained in a digital image and what humans recall after having observed an image or a group of images after some minutes. Visual descriptors are divided in two main groups: General information descriptors: contain low level descriptors which give a description about color, shape, regions, textures and motion. Specific domain information descriptors: give information about objects and events in the scene. A concrete example would be face recognition. === General information descriptors === General information descriptors consist of a set of descriptors that covers different basic and elementary features like: color, texture, shape, motion, location and others. This description is automatically generated by means of signal processing. ==== Color ==== It's the most basic quality of visual content. Five tools are defined to describe color. The three first tools represent the color distribution and the last ones describe the color relation between sequences or group of images: Dominant color descriptor (DCD) Scalable color descriptor (SCD) Color structure descriptor (CSD) Color layout descriptor (CLD) Group of frame (GoF) or group-of-pictures (GoP) ==== Texture ==== It's an important quality in order to describe an image. The texture descriptors characterize image textures or regions. They observe the region homogeneity and the histograms of these region borders. The set of descriptors is formed by: Homogeneous texture descriptor (HTD) Texture browsing descriptor (TBD) Edge histogram descriptor (EHD) ==== Shape ==== It contains important semantic information due to human's ability to recognize objects through their shape. However, this information can only be extracted by means of a segmentation similar to the one that the human visual system implements. Nowadays, such a segmentation system is not available yet, however there exists a serial of algorithms which are considered to be a good approximation. These descriptors describe regions, contours and shapes for 2D images and for 3D volumes. The shape descriptors are the following ones: Region-based shape descriptor (RSD) Contour-based shape descriptor (CSD) 3-D shape descriptor (3-D SD) ==== Motion ==== It's defined by four different descriptors which describe motion in video sequence. Motion is related to the objects motion in the sequence and to the camera motion. This last information is provided by the capture device, whereas the rest is implemented by means of image processing. The descriptor set is the following one: Motion activity descriptor (MAD) Camera motion descriptor (CMD) Motion trajectory descriptor (MTD) Warping and parametric motion descriptor (WMD and PMD) ==== Location ==== Elements location in the image is used to describe elements in the spatial domain. In addition, elements can also be located in the temporal domain: Region locator descriptor (RLD) Spatio temporal locator descriptor (STLD) === Specific domain information descriptors === These descriptors, which give information about objects and events in the scene, are not easily extractable, even more when the extraction is to be automatically done. Nevertheless, they can be manually processed. As mentioned before, face recognition is a concrete example of an application that tries to automatically obtain this information. == Descriptors applications == Among all applications, the most important ones are: Multimedia documents search engines and classifiers. Digital library: visual descriptors allow a very detailed and concrete search of any video or image by means of different search parameters. For instance, the search of films where a known actor appears, the search of videos containing the Everest mountain, etc. Personalized electronic news service. Possibility of an automatic connection to a TV channel broadcasting a soccer match, for example, whenever a player approaches the goal area. Control and filtering of concrete audiovisual content, like violent or pornographic material. Also, authorization for some multimedia content.
Read more →
Core FTP

Core FTP LE is a freeware secure FTP client for Windows, developed by CoreFTP.com. Features include FTP, SSL/TLS, SFTP via SSH, and HTTP/HTTPS support. Secure FTP clients encrypt account information and data transferred across the internet, protecting data from being seen, or sniffed across networks. Core FTP is a traditional FTP client with local files displayed on the left, remote files on the right. Core FTP Server is a secure FTP server for Windows, developed by CoreFTP.com, starting in 2010. == Licensing == CoreFTP LE is free for personal, educational, non-profit, and business use.
Read more →
Amália (LLM)

Amália is a Portuguese large language model (LLM) announced in November 2024 by the Portuguese Prime-Minister Luís Montenegro. Its final version is expected to be launched in 2026. It is being developed by Center for Responsible AI (Centro para a AI Responsável) and by the research centers of NOVA School of Science and Technology and Instituto Superior Técnico. == History == In 2024 it was announced that the Portuguese Agency for Administrative Modernization (Agência para a Modernização Administrativa) transpose this LLM to Portuguese Public Administration. According to Paulo Dimas (CEO of the Center for Responsible AI) the three fundamental points of this LLM project are the linguistic variant (European Portuguese), cultural representation and data protection. In April 2025 it was announced that Amália had entered beta phase with an improved version being expected to be launched in September 2025. The beta version released in September is available only to the Public Administration, but the website launched in October reiterates the final version will be an open model.
Read more →
Viola–Jones object detection framework

The Viola–Jones object detection framework is a machine learning object detection framework proposed in 2001 by Paul Viola and Michael Jones. It was motivated primarily by the problem of face detection, although it can be adapted to the detection of other object classes. In short, it consists of a sequence of classifiers. Each classifier is a single perceptron with several binary masks (Haar features). To detect faces in an image, a sliding window is computed over the image. For each image, the classifiers are applied. If at any point, a classifier outputs "no face detected", then the window is considered to contain no face. Otherwise, if all classifiers output "face detected", then the window is considered to contain a face. The algorithm is efficient for its time, able to detect faces in 384 by 288 pixel images at 15 frames per second on a conventional 700 MHz Intel Pentium III. It is also robust, achieving high precision and recall. While it has lower accuracy than more modern methods such as convolutional neural network, its efficiency and compact size (only around 50k parameters, compared to millions of parameters for typical CNN like DeepFace) means it is still used in cases with limited computational power. For example, in the original paper, they reported that this face detector could run on the Compaq iPAQ at 2 fps (this device has a low power StrongARM without floating point hardware). == Problem description == Face detection is a binary classification problem combined with a localization problem: given a picture, decide whether it contains faces, and construct bounding boxes for the faces. To make the task more manageable, the Viola–Jones algorithm only detects full view (no occlusion), frontal (no head-turning), upright (no rotation), well-lit, full-sized (occupying most of the frame) faces in fixed-resolution images. The restrictions are not as severe as they appear, as one can normalize the picture to bring it closer to the requirements for Viola-Jones. any image can be scaled to a fixed resolution for a general picture with a face of unknown size and orientation, one can perform blob detection to discover potential faces, then scale and rotate them into the upright, full-sized position. the brightness of the image can be corrected by white balancing. the bounding boxes can be found by sliding a window across the entire picture, and marking down every window that contains a face. This would generally detect the same face multiple times, for which duplication removal methods, such as non-maximal suppression, can be used. The "frontal" requirement is non-negotiable, as there is no simple transformation on the image that can turn a face from a side view to a frontal view. However, one can train multiple Viola-Jones classifiers, one for each angle: one for frontal view, one for 3/4 view, one for profile view, a few more for the angles in-between them. Then one can at run time execute all these classifiers in parallel to detect faces at different view angles. The "full-view" requirement is also non-negotiable, and cannot be simply dealt with by training more Viola-Jones classifiers, since there are too many possible ways to occlude a face. == Components of the framework == A full presentation of the algorithm is in. Consider an image I ( x , y ) {\displaystyle I(x,y)} of fixed resolution ( M , N ) {\displaystyle (M,N)} . Our task is to make a binary decision: whether it is a photo of a standardized face (frontal, well-lit, etc) or not. Viola–Jones is essentially a boosted feature learning algorithm, trained by running a modified AdaBoost algorithm on Haar feature classifiers to find a sequence of classifiers f 1 , f 2 , . . . , f k {\displaystyle f_{1},f_{2},...,f_{k}} . Haar feature classifiers are crude, but allows very fast computation, and the modified AdaBoost constructs a strong classifier out of many weak ones. At run time, a given image I {\displaystyle I} is tested on f 1 ( I ) , f 2 ( I ) , . . . f k ( I ) {\displaystyle f_{1}(I),f_{2}(I),...f_{k}(I)} sequentially. If at any point, f i ( I ) = 0 {\displaystyle f_{i}(I)=0} , the algorithm immediately returns "no face detected". If all classifiers return 1, then the algorithm returns "face detected". For this reason, the Viola-Jones classifier is also called "Haar cascade classifier". === Haar feature classifiers === Consider a perceptron f w , b {\displaystyle f_{w,b}} defined by two variables w ( x , y ) , b {\displaystyle w(x,y),b} . It takes in an image I ( x , y ) {\displaystyle I(x,y)} of fixed resolution, and returns f w , b ( I ) = { 1 , if ∑ x , y w ( x , y ) I ( x , y ) + b > 0 0 , else {\displaystyle f_{w,b}(I)={\begin{cases}1,\quad {\text{if }}\sum _{x,y}w(x,y)I(x,y)+b>0\\0,\quad {\text{else}}\end{cases}}} A Haar feature classifier is a perceptron f w , b {\displaystyle f_{w,b}} with a very special kind of w {\displaystyle w} that makes it extremely cheap to calculate. Namely, if we write out the matrix w ( x , y ) {\displaystyle w(x,y)} , we find that it takes only three possible values { + 1 , − 1 , 0 } {\displaystyle \{+1,-1,0\}} , and if we color the matrix with white on + 1 {\displaystyle +1} , black on − 1 {\displaystyle -1} , and transparent on 0 {\displaystyle 0} , the matrix is in one of the 5 possible patterns shown on the right. Each pattern must also be symmetric to x-reflection and y-reflection (ignoring the color change), so for example, for the horizontal white-black feature, the two rectangles must be of the same width. For the vertical white-black-white feature, the white rectangles must be of the same height, but there is no restriction on the black rectangle's height. ==== Rationale for Haar features ==== The Haar features used in the Viola-Jones algorithm are a subset of the more general Haar basis functions, which have been used previously in the realm of image-based object detection. While crude compared to alternatives such as steerable filters, Haar features are sufficiently complex to match features of typical human faces. For example: The eye region is darker than the upper-cheeks. The nose bridge region is brighter than the eyes. Composition of properties forming matchable facial features: Location and size: eyes, mouth, bridge of nose Value: oriented gradients of pixel intensities Further, the design of Haar features allows for efficient computation of f w , b ( I ) {\displaystyle f_{w,b}(I)} using only constant number of additions and subtractions, regardless of the size of the rectangular features, using the summed-area table. === Learning and using a Viola–Jones classifier === Choose a resolution ( M , N ) {\displaystyle (M,N)} for the images to be classified. In the original paper, they recommended ( M , N ) = ( 24 , 24 ) {\displaystyle (M,N)=(24,24)} . ==== Learning ==== Collect a training set, with some containing faces, and others not containing faces. Perform a certain modified AdaBoost training on the set of all Haar feature classifiers of dimension ( M , N ) {\displaystyle (M,N)} , until a desired level of precision and recall is reached. The modified AdaBoost algorithm would output a sequence of Haar feature classifiers f 1 , f 2 , . . . , f k {\displaystyle f_{1},f_{2},...,f_{k}} . The details of the modified AdaBoost algorithm is detailed below. ==== Using ==== To use a Viola-Jones classifier with f 1 , f 2 , . . . , f k {\displaystyle f_{1},f_{2},...,f_{k}} on an image I {\displaystyle I} , compute f 1 ( I ) , f 2 ( I ) , . . . f k ( I ) {\displaystyle f_{1}(I),f_{2}(I),...f_{k}(I)} sequentially. If at any point, f i ( I ) = 0 {\displaystyle f_{i}(I)=0} , the algorithm immediately returns "no face detected". If all classifiers return 1, then the algorithm returns "face detected". === Learning algorithm === The speed with which features may be evaluated does not adequately compensate for their number, however. For example, in a standard 24x24 pixel sub-window, there are a total of M = 162336 possible features, and it would be prohibitively expensive to evaluate them all when testing an image. Thus, the object detection framework employs a variant of the learning algorithm AdaBoost to both select the best features and to train classifiers that use them. This algorithm constructs a "strong" classifier as a linear combination of weighted simple “weak” classifiers. h ( x ) = sgn ⁡ ( ∑ j = 1 M α j h j ( x ) ) {\displaystyle h(\mathbf {x} )=\operatorname {sgn} \left(\sum _{j=1}^{M}\alpha _{j}h_{j}(\mathbf {x} )\right)} Each weak classifier is a threshold function based on the feature f j {\displaystyle f_{j}} . h j ( x ) = { − s j if f j < θ j s j otherwise {\displaystyle h_{j}(\mathbf {x} )={\begin{cases}-s_{j}&{\text{if }}f_{j}<\theta _{j}\\s_{j}&{\text{otherwise}}\end{cases}}} The threshold value θ j {\displaystyle \theta _{j}} and the polarity s j ∈ ± 1 {\displaystyle s_{j}\in \pm 1} are determined in the training, as well as the coefficients α j {\displaystyle \alpha _{j}} . Here a simplified version of the lea
Read more →
Cyclodisparity

In vision science, cyclodisparity is the difference in the rotation angle of an object or scene viewed by the left and right eyes. Cyclodisparity can result from the eyes' torsional rotation (cyclorotation) or can be created artificially by presenting to the eyes two images that need to be rotated relative to each other for binocular fusion to take place. == Human and animal vision == The eyes and visual system can compensate for cyclodisparity up to a certain point; if the cyclodisparity is larger than a threshold, the images cannot be fused, resulting stereoblindness, and in double vision in subjects who otherwise have full stereo vision. When a human subject is presented with images that have artificial cyclodisparity, cyclovergence is evoked, that is, a motor response of the eye muscles that rotates the two eyes in opposite directions, thereby reducing cyclodisparity. Visually-induced cyclovergence of up to 8 degrees has been observed in normal subjects. Furthermore, up to about 8 degrees can usually be compensated by purely sensory means, that is, without physical eye rotation. This means that the normal human observer can achieve binocular image fusion in presence of cyclodisparity of up to approximately 16 degrees. Cyclodisparity due to images having been rotated inward can be compensated better when the gaze is directed downwards, and cyclodisparity due to an outward rotation can be compensated better when the gaze is directed upwards. A proposed explanation for this phenomenon is that the motor system is coordinated in such a way that the eyes perform a torsional movement to reduce the size of the search zones and thus the computational load required for solving the correspondence problem. The resulting cyclovergence at near gaze is smaller than the cyclovergence predicted by Listing's law. == Video processing and computer vision == Active camera torsion can be used in machine and computer vision for several purposes. For instance, camera torsion can be used to make improved use of the search range over which matching detectors or stereo matching algorithms operate, or to make a 3D slanted surface appear frontoparallel for further stereo processing. For image compression purposes, images with cyclodisparity are advantageously encoded using global motion compensation using a rotational motion model.
Read more →
GeneRIF

A GeneRIF or Gene Reference Into Function is a short (255 characters or fewer) statement about the function of a gene. GeneRIFs provide a simple mechanism for allowing scientists to add to the functional annotation of genes described in the Entrez Gene database. In practice, function is constructed quite broadly. For example, there are GeneRIFs that discuss the role of a gene in a disease, GeneRIFs that point the viewer towards a review article about the gene, and GeneRIFs that discuss the structure of a gene. However, the stated intent is for GeneRIFs to be about gene function. Currently over half a million geneRIFs have been created for genes from almost 1000 different species. GeneRIFs are always associated with specific entries in the Entrez Gene database. Each GeneRIF has a pointer to the PubMed ID (a type of document identifier) of a scientific publication that provides evidence for the statement made by the GeneRIF. GeneRIFs are often extracted directly from the document that is identified by the PubMed ID, very frequently from its title or from its final sentence. GeneRIFs are usually produced by NCBI indexers, but anyone may submit a GeneRIF. To be processed, a valid Gene ID must exist for the specific gene, or the Gene staff must have assigned an overall Gene ID to the species. The latter case is implemented via records in Gene with the symbol NEWENTRY. Once the Gene ID is identified, only three types of information are required to complete a submission: a concise phrase describing a function or functions (less than 255 characters in length, preferably more than a restatement of the title of the paper); a published paper describing that function, implemented by supplying the PubMed ID of a citation in PubMed; a valid e-mail address (which will remain confidential). == Example == Here are some GeneRIFs taken from Entrez Gene for GeneID 7157, the human gene TP53. The PubMed document identifiers have been omitted from the examples. Note the wide variability with respect to the presence or absence of punctuation and of sentence-initial capital letters. p53 and c-erbB-2 may have independent role in carcinogenesis of gall bladder cancer Degradation of endogenous HIPK2 depends on the presence of a functional p53 protein. p53 codon 72 alleles influence the response to anticancer drugs in cells from aged people by regulating the cell cycle inhibitor p21WAF1 Logistic regression analysis showed p53 and COX-2 as dependent predictors in pancreatic carcinogenesis, and a reciprocal relationship to neoplastic progression between p53 and COX-2. GeneRIFs are an unusual type of textual genre, and they have recently been the subject of a number of articles from the natural language processing community.
Read more →
Calais (Reuters product)

Calais is a service created by Thomson Reuters that automatically extracts semantic information from web pages in a format that can be used on the semantic web. Calais was launched in January 2008, and is free to use. The technology is now available via the website of Refinitiv, a provider of financial market data and infrastructure founded in 2018, that is a subsidiary of London Stock Exchange Group. The Calais Web service reads unstructured text and returns Resource Description Framework formatted results identifying entities, facts and events within the text. The service appears to be based on technology acquired when Reuters purchased ClearForest in 2007. The technology has also been used to automatically tag blog articles, and organize museum collections. Calais uses natural language processing technologies delivered via a web service interface.
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 →
BERT (language model)

Bidirectional encoder representations from transformers (BERT) is a language model introduced in October 2018 by researchers at Google. It learns to represent text as a sequence of vectors using self-supervised learning. It uses the encoder-only transformer architecture. BERT dramatically improved the state of the art for large language models. As of 2020, BERT is a ubiquitous baseline in natural language processing (NLP) experiments. BERT is trained by masked token prediction and next sentence prediction. With this training, BERT learns contextual, latent representations of tokens in their context, similar to ELMo and GPT-2. It found applications for many natural language processing tasks, such as coreference resolution and polysemy resolution. It improved on ELMo and spawned the study of "BERTology", which attempts to interpret what is learned by BERT. BERT was originally implemented in the English language at two model sizes, BERTBASE (110 million parameters) and BERTLARGE (340 million parameters). Both were trained on the Toronto BookCorpus (800M words) and English Wikipedia (2,500M words). The weights were released on GitHub. On March 11, 2020, 24 smaller models were released, the smallest being BERTTINY with just 4 million parameters. == Architecture == BERT is an "encoder-only" transformer architecture. At a high level, BERT consists of 4 modules: Tokenizer: This module converts a piece of English text into a sequence of integers ("tokens"). Embedding: This module converts the sequence of tokens into an array of real-valued vectors representing the tokens. It represents the conversion of discrete token types into a lower-dimensional Euclidean space. Encoder: a stack of Transformer blocks with self-attention, but without causal masking. Task head: This module converts the final representation vectors into one-shot encoded tokens again by producing a predicted probability distribution over the token types. It can be viewed as a simple decoder, decoding the latent representation into token types, or as an "un-embedding layer". The task head is necessary for pre-training, but it is often unnecessary for so-called "downstream tasks," such as question answering or sentiment classification. Instead, one removes the task head and replaces it with a newly initialized module suited for the task, and finetune the new module. The latent vector representation of the model is directly fed into this new module, allowing for sample-efficient transfer learning. === Embedding === This section describes the embedding used by BERTBASE. The other one, BERTLARGE, is similar, just larger. The tokenizer of BERT is WordPiece, which is a sub-word strategy like byte-pair encoding. Its vocabulary size is 30,000, and any token not appearing in its vocabulary is replaced by [UNK] ("unknown"). The first layer is the embedding layer, which contains three components: token type embeddings, position embeddings, and segment type embeddings. Token type: The token type is a standard embedding layer, translating a one-hot vector into a dense vector based on its token type. Position: The position embeddings are based on a token's position in the sequence. BERT uses absolute position embeddings, where each position in a sequence is mapped to a real-valued vector. Each dimension of the vector consists of a sinusoidal function that takes the position in the sequence as input. Segment type: Using a vocabulary of just 0 or 1, this embedding layer produces a dense vector based on whether the token belongs to the first or second text segment in that input. In other words, type-1 tokens are all tokens that appear after the [SEP] special token. All prior tokens are type-0. The three embedding vectors are added together representing the initial token representation as a function of these three pieces of information. After embedding, the vector representation is normalized using a LayerNorm operation, outputting a 768-dimensional vector for each input token. After this, the representation vectors are passed forward through 12 Transformer encoder blocks, and are decoded back to 30,000-dimensional vocabulary space using a basic affine transformation layer. === Architectural family === The encoder stack of BERT has 2 free parameters: L {\displaystyle L} , the number of layers, and H {\displaystyle H} , the hidden size. There are always H / 64 {\displaystyle H/64} self-attention heads, and the feed-forward/filter size is always 4 H {\displaystyle 4H} . By varying these two numbers, one obtains an entire family of BERT models. For BERT: the feed-forward size and filter size are synonymous. Both of them denote the number of dimensions in the middle layer of the feed-forward network. the hidden size and embedding size are synonymous. Both of them denote the number of real numbers used to represent a token. The notation for encoder stack is written as L/H. For example, BERTBASE is written as 12L/768H, BERTLARGE as 24L/1024H, and BERTTINY as 2L/128H. == Training == === Pre-training === BERT was pre-trained simultaneously on two tasks: Masked language modeling (MLM): In this task, BERT ingests a sequence of words, where one word may be randomly changed ("masked"), and BERT tries to predict the original words that had been changed. For example, in the sentence "The cat sat on the [MASK]," BERT would need to predict "mat." This helps BERT learn bidirectional context, meaning it understands the relationships between words not just from left to right or right to left but from both directions at the same time. Next sentence prediction (NSP): In this task, BERT is trained to predict whether one sentence logically follows another. For example, given two sentences, "The cat sat on the mat" and "It was a sunny day", BERT has to decide if the second sentence is a valid continuation of the first one. This helps BERT understand relationships between sentences, which is important for tasks like question answering or document classification. ==== Masked language modeling ==== In masked language modeling, 15% of tokens would be randomly selected for masked-prediction task, and the training objective was to predict the masked token given its context. In more detail, the selected token is: replaced with a [MASK] token with probability 80%, replaced with a random word token with probability 10%, not replaced with probability 10%. The reason not all selected tokens are masked is to avoid the dataset shift problem. The dataset shift problem arises when the distribution of inputs seen during training differs significantly from the distribution encountered during inference. A trained BERT model might be applied to word representation (like Word2Vec), where it would be run over sentences not containing any [MASK] tokens. It is later found that more diverse training objectives are generally better. As an illustrative example, consider the sentence "my dog is cute". It would first be divided into tokens like "my1 dog2 is3 cute4". Then a random token in the sentence would be picked. Let it be the 4th one "cute4". Next, there would be three possibilities: with probability 80%, the chosen token is masked, resulting in "my1 dog2 is3 [MASK]4"; with probability 10%, the chosen token is replaced by a uniformly sampled random token, such as "happy", resulting in "my1 dog2 is3 happy4"; with probability 10%, nothing is done, resulting in "my1 dog2 is3 cute4". After processing the input text, the model's 4th output vector is passed to its decoder layer, which outputs a probability distribution over its 30,000-dimensional vocabulary space. ==== Next sentence prediction ==== Given two sentences, the model predicts if they appear sequentially in the training corpus, outputting either [IsNext] or [NotNext]. During training, the algorithm sometimes samples two sentences from a single continuous span in the training corpus, while at other times, it samples two sentences from two discontinuous spans. The first sentence starts with a special token, [CLS] (for "classify"). The two sentences are separated by another special token, [SEP] (for "separate"). After processing the two sentences, the final vector for the [CLS] token is passed to a linear layer for binary classification into [IsNext] and [NotNext]. For example: Given "[CLS] my dog is cute [SEP] he likes playing [SEP]", the model should predict [IsNext]. Given "[CLS] my dog is cute [SEP] how do magnets work [SEP]", the model should predict [NotNext]. === Fine-tuning === BERT is meant as a general pretrained model for various applications in natural language processing. That is, after pre-training, BERT can be fine-tuned with fewer resources on smaller datasets to optimize its performance on specific tasks such as natural language inference and text classification, and sequence-to-sequence-based language generation tasks such as question answering and conversational response generation. The original BERT paper published results demonstrating that a small amount of fine
Read more →
Keyword extraction

Keyword extraction is tasked with the automatic identification of terms that best describe the subject of a document. Key phrases, key terms, key segments or just keywords are the terminology which is used for defining the terms that represent the most relevant information contained in the document. Although the terminology is different, function is the same: characterization of the topic discussed in a document. The task of keyword extraction is an important problem in text mining, information extraction, information retrieval and natural language processing (NLP). == Keyword assignment vs. extraction == Keyword assignment methods can be roughly divided into: keyword assignment (keywords are chosen from controlled vocabulary or taxonomy) and keyword extraction (keywords are chosen from words that are explicitly mentioned in original text). Methods for automatic keyword extraction can be supervised, semi-supervised, or unsupervised. Unsupervised methods can be further divided into simple statistics, linguistics or graph-based, or ensemble methods that combine some or most of these methods.
Read more →
Phrase structure grammar

The term phrase structure grammar was originally introduced by Noam Chomsky as the term for grammar studied previously by Emil Post and Axel Thue (Post canonical systems). Some authors, however, reserve the term for more restricted grammars in the Chomsky hierarchy: context-sensitive grammars or context-free grammars. In a broader sense, phrase structure grammars are also known as constituency grammars. The defining character of phrase structure grammars is thus their adherence to the constituency relation, as opposed to the dependency relation of dependency grammars. == History == In 1956, Chomsky wrote, "A phrase-structure grammar is defined by a finite vocabulary (alphabet) Vp, and a finite set Σ of initial strings in Vp, and a finite set F of rules of the form: X → Y, where X and Y are strings in Vp." == Constituency relation == In linguistics, phrase structure grammars are all those grammars that are based on the constituency relation, as opposed to the dependency relation associated with dependency grammars; hence, phrase structure grammars are also known as constituency grammars. Any of several related theories for the parsing of natural language qualify as constituency grammars, and most of them have been developed from Chomsky's work, including Government and binding theory Generalized phrase structure grammar Head-driven phrase structure grammar Lexical functional grammar The minimalist program Nanosyntax Further grammar frameworks and formalisms also qualify as constituency-based, although they may not think of themselves as having spawned from Chomsky's work, e.g. Arc pair grammar, and Categorial grammar.
Read more →
Calais (Reuters product)

Calais is a service created by Thomson Reuters that automatically extracts semantic information from web pages in a format that can be used on the semantic web. Calais was launched in January 2008, and is free to use. The technology is now available via the website of Refinitiv, a provider of financial market data and infrastructure founded in 2018, that is a subsidiary of London Stock Exchange Group. The Calais Web service reads unstructured text and returns Resource Description Framework formatted results identifying entities, facts and events within the text. The service appears to be based on technology acquired when Reuters purchased ClearForest in 2007. The technology has also been used to automatically tag blog articles, and organize museum collections. Calais uses natural language processing technologies delivered via a web service interface.
Read more →
Deep learning

In machine learning, deep learning (DL) focuses on utilizing multilayered neural networks to perform tasks such as classification, regression, and representation learning. The field takes inspiration from biological neuroscience and revolves around stacking artificial neurons into layers and "training" them to process data. The adjective "deep" refers to the use of multiple layers (ranging from three to several hundred or thousands) in the network. Methods used can be supervised, semi-supervised or unsupervised. Some common deep learning network architectures include fully connected networks, deep belief networks, recurrent neural networks, convolutional neural networks, generative adversarial networks, transformers, and neural radiance fields. These architectures have been applied to fields including computer vision, speech recognition, natural language processing, machine translation, bioinformatics, drug design, medical image analysis, climate science, material inspection and board game programs, where they have produced results comparable to and in some cases surpassing human expert performance. Early forms of neural networks were inspired by information processing and distributed communication nodes in biological systems, particularly the human brain. However, current neural networks do not intend to model the brain function of organisms, and are generally seen as low-quality models for that purpose. == Overview == Most modern deep learning models are based on multi-layered neural networks such as convolutional neural networks and transformers, although they can also include propositional formulas or latent variables organized layer-wise in deep generative models such as the nodes in deep belief networks and deep Boltzmann machines. Fundamentally, deep learning refers to a class of machine learning algorithms in which a hierarchy of layers is used to transform input data into a progressively more abstract and composite representation. For example, in an image recognition model, the raw input may be an image (represented as a tensor of pixels). The first representational layer may attempt to identify basic shapes such as lines and circles, the second layer may compose and encode arrangements of edges, the third layer may encode a nose and eyes, and the fourth layer may recognize that the image contains a face. Importantly, a deep learning process can learn which features to optimally place at which level on its own. Prior to deep learning, machine learning techniques often involved hand-crafted feature engineering to transform the data into a more suitable representation for a classification algorithm to operate on. In the deep learning approach, features are not hand-crafted and the model discovers useful feature representations from the data automatically. This does not eliminate the need for hand-tuning; for example, varying numbers of layers and layer sizes can provide different degrees of abstraction. The word "deep" in "deep learning" refers to the number of layers through which the data is transformed. More precisely, deep learning systems have a substantial credit assignment path (CAP) depth. The CAP is the chain of transformations from input to output. CAPs describe potentially causal connections between input and output. For a feedforward neural network, the depth of the CAPs is that of the network and is the number of hidden layers plus one (as the output layer is also parameterized). For recurrent neural networks, in which a signal may propagate through a layer more than once, the CAP depth is potentially unlimited. No universally agreed-upon threshold of depth divides shallow learning from deep learning, but most researchers agree that deep learning involves CAP depth higher than two. CAP of depth two has been shown to be a universal approximator in the sense that it can emulate any function. Beyond that, more layers do not add to the function approximator ability of the network. Deep models (CAP > two) are able to extract better features than shallow models and hence, extra layers help in learning the features effectively. Deep learning architectures can be constructed with a greedy layer-by-layer method. Deep learning helps to disentangle these abstractions and pick out which features improve performance. Deep learning algorithms can be applied to unsupervised learning tasks. This is an important benefit because unlabeled data is more abundant than labeled data. Examples of deep structures that can be trained in an unsupervised manner are deep belief networks. The term deep learning was introduced to the machine learning community by Rina Dechter in 1986, and to artificial neural networks by Igor Aizenberg and colleagues in 2000, in the context of Boolean threshold neurons. The etymology of the term is more complicated. == Interpretations == Deep neural networks are generally interpreted in terms of the universal approximation theorem or probabilistic inference. The classic universal approximation theorem concerns the capacity of feedforward neural networks with a single hidden layer of finite size to approximate continuous functions. In 1989, the first proof was published by George Cybenko for sigmoid activation functions and was generalised to feed-forward multi-layer architectures in 1991 by Kurt Hornik. Recent work also showed that universal approximation also holds for non-bounded activation functions such as Kunihiko Fukushima's rectified linear unit. The universal approximation theorem for deep neural networks concerns the capacity of networks with bounded width but the depth is allowed to grow. Lu et al. proved that if the width of a deep neural network with ReLU activation is strictly larger than the input dimension, then the network can approximate any Lebesgue integrable function; if the width is smaller or equal to the input dimension, then a deep neural network is not a universal approximator. The probabilistic interpretation derives from the field of machine learning. It features inference, as well as the optimization concepts of training and testing, related to fitting and generalization, respectively. More specifically, the probabilistic interpretation considers the activation nonlinearity as a cumulative distribution function. The probabilistic interpretation led to the introduction of dropout as regularizer in neural networks. The probabilistic interpretation was introduced by researchers including Hopfield, Widrow and Narendra and popularized in surveys such as the one by Bishop. == History == === Before 1980 === There are two types of artificial neural network (ANN): feedforward neural network (FNN) or multilayer perceptron (MLP) and recurrent neural networks (RNN). RNNs have cycles in their connectivity structure, whereas FNNs do not. In the 1920s, Wilhelm Lenz and Ernst Ising created the Ising model which is essentially a non-learning RNN architecture consisting of neuron-like threshold elements. In 1972, Shun'ichi Amari made this architecture adaptive. His learning RNN was republished by John Hopfield in 1982. Other early recurrent neural networks were published by Kaoru Nakano in 1971. Already in 1948, Alan Turing produced work on "Intelligent Machinery" that was not published in his lifetime, containing "ideas related to artificial evolution and learning RNNs". Frank Rosenblatt (1958) proposed the perceptron, an MLP with 3 layers: an input layer, a hidden layer with randomized weights that did not learn, and an output layer. He later published a 1962 book that also introduced variants and computer experiments, including a version with four-layer perceptrons "with adaptive preterminal networks" where the last two layers have learned weights (here he credits H. D. Block and B. W. Knight). The book cites an earlier network by R. D. Joseph (1960) "functionally equivalent to a variation of" this four-layer system (the book mentions Joseph over 30 times). Should Joseph therefore be considered the originator of proper adaptive multilayer perceptrons with learning hidden units? Unfortunately, the learning algorithm was not a functional one, and fell into oblivion. The first working deep learning algorithm was the Group method of data handling, a method to train arbitrarily deep neural networks, published by Alexey Ivakhnenko and Lapa in 1965. They regarded it as a form of polynomial regression, or a generalization of Rosenblatt's perceptron to handle more complex, nonlinear, and hierarchical relationships. A 1971 paper described a deep network with eight layers trained by this method, which is based on layer by layer training through regression analysis. Superfluous hidden units are pruned using a separate validation set. Since the activation functions of the nodes are Kolmogorov-Gabor polynomials, these were also the first deep networks with multiplicative units or "gates". The first deep learning multilayer perceptron trained by stochastic gradient descent was published in 1967 by Shun'ichi
Read more →