AI Detector In Photos

AI Detector In Photos — independent reviews, comparisons, pricing and step-by-step guides on Aizhi.

Vujak

VuJak is an early video sampler, a VJ remix and mashup tool created in 1992 by Brian Kane, Lisa Eisenpresser, and Jay Haynes. The original name of the project was Mideo, but it was later changed to VuJak. VuJak was based on MIDI control of video in real-time. It was created with MAX from Opcode Systems, and utilized the newly released QuickTime 1.0 movie object. The first working version of the program was built on a Mac IIfx with 8 megs of ram, and could jump in real-time across a 160 x 120 pixel QuickTime movie via a midi keyboard. Later versions could manipulate full screen video, included the first real-time video scratch feature, had looping, vari-speed, and random play features, and allowed for recording and editing of video sequences within the application. VuJak also had networking capabilities which allowed artists to "jam" in real time across standard phone lines. The first public exhibition of VuJak was at the Digital Hollywood conference in Beverly Hills in 1993, where it was promoted by Timothy Leary. VuJak was featured in Mondo 2000, CBS Evening News, Wired Magazine, Electronic Musician, Billboard Magazine, The Hollywood Reporter, and it was used to create promotional videos for MTV. In 1994, VuJak was a featured interactive exhibition at the Exploratorium in San Francisco. Development of VuJak ceased in 1995.
Read more →
Resilience (mathematics)

In mathematical modeling, resilience refers to the ability of a dynamical system to recover from perturbations and return to its original stable steady state. It is a measure of the stability and robustness of a system in the face of changes or disturbances. If a system is not resilient enough, it is more susceptible to perturbations and can more easily undergo a critical transition. A common analogy used to explain the concept of resilience of an equilibrium is one of a ball in a valley. A resilient steady state corresponds to a ball in a deep valley, so any push or perturbation will very quickly lead the ball to return to the resting point where it started. On the other hand, a less resilient steady state corresponds to a ball in a shallow valley, so the ball will take a much longer time to return to the equilibrium after a perturbation. The concept of resilience is particularly useful in systems that exhibit tipping points, whose study has a long history that can be traced back to catastrophe theory. While this theory was initially overhyped and fell out of favor, its mathematical foundation remains strong and is now recognized as relevant to many different systems. == History == In 1973, Canadian ecologist C. S. Holling proposed a definition of resilience in the context of ecological systems. According to Holling, resilience is "a measure of the persistence of systems and of their ability to absorb change and disturbance and still maintain the same relationships between populations or state variables". Holling distinguished two types of resilience: engineering resilience and ecological resilience. Engineering resilience refers to the ability of a system to return to its original state after a disturbance, such as a bridge that can be repaired after an earthquake. Ecological resilience, on the other hand, refers to the ability of a system to maintain its identity and function despite a disturbance, such as a forest that can regenerate after a wildfire while maintaining its biodiversity and ecosystem services. With time, the once well-defined and unambiguous concept of resilience has experienced a gradual erosion of its clarity, becoming more vague and closer to an umbrella term than a specific concrete measure. == Definition == Mathematically, resilience can be approximated by the inverse of the return time to an equilibrium given by resilience ≡ − Re ( λ 1 ( A ) ) {\displaystyle {\text{resilience}}\equiv -{\text{Re}}(\lambda _{1}({\textbf {A}}))} where λ 1 {\textstyle \lambda _{1}} is the maximum eigenvalue of matrix A {\textstyle {\textbf {A}}} . The largest this value is, the faster a system returns to the original stable steady state, or in other words, the faster the perturbations decay. == Applications and examples == In ecology, resilience might refer to the ability of the ecosystem to recover from disturbances such as fires, droughts, or the introduction of invasive species. A resilient ecosystem would be one that is able to adapt to these changes and continue functioning, while a less resilient ecosystem might experience irreversible damage or collapse. The exact definition of resilience has remained vague for practical matters, which has led to a slow and proper application of its insights for management of ecosystems. In epidemiology, resilience may refer to the ability of a healthy community to recover from the introduction of infected individuals. That is, a resilient system is more likely to remain at the disease-free equilibrium after the invasion of a new infection. Some stable systems exhibit critical slowing down where, as they approach a basic reproduction number of 1, their resilience decreases, hence taking a longer time to return to the disease-free steady state. Resilience is an important concept in the study of complex systems, where there are many interacting components that can affect each other in unpredictable ways. Mathematical models can be used to explore the resilience of such systems and to identify strategies for improving their resilience in the face of environmental or other changes. For example, when modelling networks it is often important to be able to quantify network resilience, or network robustness, to the loss of nodes. Scale-free networks are particularly resilient since most of their nodes have few links. This means that if some nodes are randomly removed, it is more likely that the nodes with fewer connections are taken out, thus preserving the key properties of the network.
Read more →
Project Maven

Project Maven (officially Algorithmic Warfare Cross Functional Team) is a United States Department of Defense initiative launched in 2017 to accelerate the adoption of machine learning and data integration across U.S. military intelligence workflows, specifically in intelligence, surveillance, target acquisition, and reconnaissance as well as in geospatial intelligence. It initially focused on applying computer vision for processing images and videos for intelligence purposes. Currently, the program operates under the National Geospatial-Intelligence Agency (NGA) and encompasses multiple applications across the Department of Defense spanning military operation targeting support, data integration and visualization for analysts, and training machine learning models on labeled datasets of military assets and infrastructure. It integrates data from drones, satellites, and other sensors to flag potential targets, present findings to human analysts, and relay their decisions to operational systems. The program originated under Deputy Secretary Robert O. Work after he raised concerns about China's advances in defense applications of artificial intelligence. Project leaders, Colonel Drew Cukor, USMC, and Lt. Gen. Jack Shanahan, framed the program as human-in-the-loop decision support inside the Department of Defense rather than as an autonomous weapons platform. Contractors supporting Maven have included Google, which withdrew in 2018 after internal protests, and follow-on integrators such as Palantir, Anduril, Amazon Web Services, and Anthropic (withdrew in 2026). The Pentagon credits Maven with providing 2024 targeting support for U.S. airstrikes in Iraq, Syria, and Yemen, along with locating hostile maritime assets in the Red Sea. == Administrative history == Initially, the effort was led by Robert O. Work who was concerned about China's military use of the emerging technology. Reportedly, Pentagon development stops short of acting as an AI weapons system capable of firing on self-designated targets. The project was established in a memo by the U.S. Deputy Secretary of Defense on 26 April 2017 proposing an "Algorithmic Warfare Cross-Functional Team". With the help of Defense Innovation Unit, the project obtained the support of top talents in AI outside of the traditional defense contracting base. It was initially funded for $70 million. Jack Shanahan was the director of the project during April 2017 to December 2018. At the second Defense One Tech Summit in July 2017, Cukor said that the investment in a "deliberate workflow process" was funded by the Department [of Defense] through its "rapid acquisition authorities" for about "the next 36 months". In the defense industry, the standard procedure for the military to acquire hardware is by way of research, development, test, and evaluation (RDT&E), followed by production and sustainment. In 2017, acquiring software was done in the same way as hardware. This created a problem, since software is constantly updated. Project Maven procured software using Broad Agency Announcements, a flexible contracting vehicle that categorized software as consistently RDT&E, allowing constant updating. Another issue was that the government usually acquired the intellectual property (IP) for procured software, and with the project, only parts of the IP of the software was acquired. Cukor used the principle of "platform IP belongs to the vendor, configurations on top are the customer's". For example, Palantir retained IP to their core platform, while the government obtained the IP to Maven-specific logic configured on top of it. According to US Air Force Lt. Gen. Jack Shanahan in November 2017, it is "designed to be that pilot project, that pathfinder, that spark that kindles the flame front of artificial intelligence across the rest of the [Defense] Department". Its chief, U.S. Marine Corps Col. Drew Cukor, said: "People and computers will work symbiotically to increase the ability of weapon systems to detect objects." Project Maven has been noted by allies, such as Australia's Ian Langford, for the ability to identify adversaries by harvesting data from sensors on UAVs and satellites. As of 2017 December, 150,000 images had been manually labelled to establish the first training data sets, and it was projected to reach one million by January 2018. Project Maven was funded for $221 million in fiscal 2020. In 2020, the House and Senate conferees on the National Defense Authorization Act for Fiscal Year 2021, agreed to the Senate's recommendation to fund the Pentagon's $250 million request for Project Maven. At the GEOINT Symposium of 2022, it was announced that Project Maven was transferred from the Office of the Under Secretary of Defense for Intelligence and Security to the NGA, under President Biden’s proposed budget for Fiscal Year 2023. It became a Program of Record on 2023 November 7. Frank "Trey" Whitworth, vice admiral, was the director of NGA from June 2022 to November 2025. Whitworth was initially skeptical of the program, suspecting it was incautious about the targeting principles, but later regarded it as "important work". As of 2024, the project is jointly administered by the NGA and the CDAO, and its director is Rachel Martin. Before 2025, Biden appointees within CDAO had held back AI development for safety and reliability concerns, though as of 2025, this has stopped. As of 2024, Maven provided the cloud infrastructure, software capabilities, and AI for CDAO's Combined Joint All-Domain Command and Control initiatives. As of summer 2025, there were eight Maven initiatives. Of these, five were in the NGA, including analyzing drone feeds and satellite imagery. On 18 September 2025, the UK government announced a new partnership with Palantir to develop AI-powered military capabilities for decision-making and targeting, identifying opportunities worth up to £750 million over five years. On 25 March 2025, the NATO Communications and Information Agency and Palantir finalized the acquisition of the Palantir Maven Smart System NATO (MSS NATO) for employment within NATO's Allied Command Operations. It was planned to be used within 30 days of acquisition. In a letter to Pentagon on 9 March 2026, Steve Feinberg stated that Project Maven will become an official program of record by September 2026, the close of the current fiscal year. The project would transfer from the NGA to the CDAO within 30 days. Future contracting with Palantir would be handled by the US Army. In 2026-03, it was announced that the US Army Combined Arms Command would integrate Maven into its training. == Technology == Project Maven uses machine learning algorithms to analyze and fuse vast amounts of surveillance data from multiple sources made possible through data integration using Palantir Technologies. The data sources include photographs, satellite imagery, geolocation data (IP address, geotag, metadata, etc) from communications intercepts, infrared sensors, synthetic-aperture radar, and more. The system is mainly used for assisting analysts in intelligence, surveillance, target acquisition, and reconnaissance. Machine learning systems, including object recognition systems, process the data and identify potential targets, such as enemy tanks or location of new military facility. The training dataset included at least 4 million images of military objects such as warships, labelled by humans. The user interface is called Maven Smart System. It could display information such as aircraft movements, logistics, locations of key personnel, locations on the no-strike list, ships, etc. Yellow-outlined boxes show potential targets. Blue-outlined boxes show friendly forces or no-strike zones. It could also transmit, directly to weapons, a human decision to fire weapons. Internal documentation referred to "Maven ATR: automatic target recognition". Initially the project focused on applications of computer vision. The project's leaders were particularly impressed by model performance on ImageNet. As of 2018, the purpose of the system was AI-enabled analysis of full-motion video. In 2022 it expanded to combatant commands under the AI and Data Acceleration Initiative. In 2022, it was reported that the project expanded to non-image data, including captured enemy material, maritime intelligence, and publicly available information. In 2024, it was stated that Maven's key technical contribution was data management: Maven standardizes heterogeneous data through an ontology layer so data can be fused, exchanged across cloud and edge systems, and used by multiple applications. The system was presented as a broader data-centric warfighting system that feeds apps for planning, preparing, and executing operations. In 2024, the Broad Area Surveillance-Targeting (BAS-T) is a part of Maven. The system detects objects in images and uses data fusion to produce a common operational picture containing "priority based, in-depth assessment of the enemy systems pre
Read more →
Sasha Stiles

Sasha Stiles (born 1980) is an American artist and poet. After discovering natural language processing, she created the 2021 poetry collection Technelegy through an eponymous AI model, before presenting the 2025–2026 installation A Living Poem at the Museum of Modern Art. In addition to artificial intelligence, binary code and non-fungible tokens have been important aspects of her work. == Biography == Stiles was born in 1980 in Pasadena, California, to documentary filmmaker parents whose work includes Cosmos: A Personal Voyage. She was interested in science fiction during her youth, particularly how they addressed human-machine collaboration and posthumanism. She graduated magna cum laude from Harvard University with a Bachelor of Arts in 2002 and she graduated with high honors from the University of Oxford with a Master of Studies in 2004. Originally, Stiles's poetry focused on technology. In 2017, she discovered natural language processing, piquing her interest in its ability to process thoughts and words comparably to its human counterparts. Despite lacking a technological background, she managed to channel people like Gwern Branwen, Ross Goodwin, and Allison Parrish as inspirations for her AI work, and in 2019, she started training an AI model named Technelegy. In 2021, Black Spring Press published her poetry collection Technelegy, where she combines AI-generated content produced by the titular AI model with her own traditionally-created work; the AI-generated content was produced by processing Stiles's own poetry onto GPT-2 and GPT-3. She and Technelegy later co-created A Living Poem, which ran at the Museum of Modern Art's Hyundai Card Digital Wall from September 2025 to March 2026. Stiles also has used non-fungible tokens as a platform for her poetry, having been inspired to go into blockchain by her experiences working with a metaverse exhibition curated by Jess Conatser. She has used Christie's and SuperRare to sell several of her poems as tokenized real-world assets, including Daughter of E.V.E. (Ex-Vivo Uterine Environment), a 2021 single-channel video using freeze-frame shots to hide poetry. In 2021, she co-founded TheVerseVerse (stylized as theVERSEverse), a non-fungible token gallery specializing in poetry. She later created Four Core Texts: Humanifesto and Other Poems, involving four NFT videos of poetry written in looping handwriting and powered by Technelegy. Stiles uses binary code as an inspiration for her work, citing in part its "quite antagonistic system of a binary 'EITHER / OR'", which she connected to several dichotomies pitting humanity and the present against technology and the future. In 2018, she started Analog Binary Code, where she creates sculptures by arranging objects in binary code ciphers. She also created Cursive Binary, where she combines binary with cursive handwriting, after writing zeros and ones on a steamed wall while showering. Stiles and the robot BINA48 co-created the 2020 ArtYard exhibition A Valentine for the Future. She was part of the 2021 group exhibition Computational Poetics at the Beall Center for Art and Technology. From February 24 to March 18, 2023, she held her solo show Binary Odes (stylized as B1NARY 0DES) at Annka Kultys Gallery. By 2024, her work had appeared in places such as Gucci storefronts and Times Square billboards. She designed Words Beyond Words, the official poster for Art Basel in Basel 2025. Stiles is based in Milford, New Jersey, where she lives with her husband, musician Kris Bones. She has also lived in Jersey City and Bucks County, Pennsylvania. She is Kalmyk-American on her mother's side, and she has also announced plans to create a version of Technelegy in her ancestral language Kalmyk.
Read more →
Texture artist

A texture artist is an individual who develops textures for digital media, usually for video games, movies, web sites and television shows or things like 3D posters. These textures can be in the form of 2D or (rarely) 3D art that may be overlaid onto a polygon mesh to create a realistic 3D model. Texture artists often take advantage of web sites for the purposes of marketing their art and self-promotion of their skills with the goal of gaining employment from a professional game studio or to join a team working on a "mod" (modification) of an existing game in hopes of establishing industry or trade credentials.
Read more →
Tag (metadata)

In information systems, a tag is a keyword or term assigned to a piece of information (such as an Internet bookmark, multimedia, database record, or computer file). This kind of metadata helps describe an item and allows it to be found again by browsing or searching. Tags are generally chosen informally and personally by the item's creator or by its viewer, depending on the system, although they may also be chosen from a controlled vocabulary. Tagging was popularized by websites associated with Web 2.0 and is an important feature of many Web 2.0 services. It is now also part of other database systems, desktop applications, and operating systems. == Overview == People use tags to aid classification, mark ownership, note boundaries, and indicate online identity. Tags may take the form of words, images, or other identifying marks. An analogous example of tags in the physical world is museum object tagging. People were using textual keywords to classify information and objects long before computers. Computer based search algorithms made the use of such keywords a rapid way of exploring records. Tagging gained popularity due to the growth of social bookmarking, image sharing, and social networking websites. These sites allow users to create and manage labels (or "tags") that categorize content using simple keywords. Websites that include tags often display collections of tags as tag clouds, as do some desktop applications. On websites that aggregate the tags of all users, an individual user's tags can be useful both to them and to the larger community of the website's users. Tagging systems have sometimes been classified into two kinds: top-down and bottom-up. Top-down taxonomies are created by an authorized group of designers (sometimes in the form of a controlled vocabulary), whereas bottom-up taxonomies (called folksonomies) are created by all users. This definition of "top down" and "bottom up" should not be confused with the distinction between a single hierarchical tree structure (in which there is one correct way to classify each item) versus multiple non-hierarchical sets (in which there are multiple ways to classify an item); the structure of both top-down and bottom-up taxonomies may be either hierarchical, non-hierarchical, or a combination of both. Some researchers and applications have experimented with combining hierarchical and non-hierarchical tagging to aid in information retrieval. Others are combining top-down and bottom-up tagging, including in some large library catalogs (OPACs) such as WorldCat. When tags or other taxonomies have further properties (or semantics) such as relationships and attributes, they constitute an ontology. In folder system a file cannot exist in two or more folders so tag system has been thought more convenient. But transitioning to tag system requires awareness of difference between properties of two systems. In folder system the information of classification is put outside of the file and we can change folder at once. In tag system the information of classification is put inside the file so changing its tag means changing the file and it needs to be saved again and takes time. Metadata tags as described in this article should not be confused with the use of the word "tag" in some software to refer to an automatically generated cross-reference; examples of the latter are tags tables in Emacs and smart tags in Microsoft Office. == History == The use of keywords as part of an identification and classification system long predates computers. Paper data storage devices, notably edge-notched cards, that permitted classification and sorting by multiple criteria were already in use prior to the twentieth century, and faceted classification has been used by libraries since the 1930s. In the late 1970s and early 1980s, Emacs, the text editor for Unix systems, offered a companion software program called Tags that could automatically build a table of cross-references called a tags table that Emacs could use to jump between a function call and that function's definition. This use of the word "tag" did not refer to metadata tags, but was an early use of the word "tag" in software to refer to a word index. Online databases and early websites deployed keyword tags as a way for publishers to help users find content. In the early days of the World Wide Web, the keywords meta element was used by web designers to tell web search engines what the web page was about, but these keywords were only visible in a web page's source code and were not modifiable by users. In 1997, the collaborative portal "A Description of the Equator and Some ØtherLands" produced by documenta X, Germany, used the folksonomic term Tag for its co-authors and guest authors on its Upload page. In "The Equator" the term Tag for user-input was described as an abstract literal or keyword to aid the user. However, users defined singular Tags, and did not share Tags at that point. In 2003, the social bookmarking website Delicious provided a way for its users to add "tags" to their bookmarks (as a way to help find them later); Delicious also provided browseable aggregated views of the bookmarks of all users featuring a particular tag. Within a couple of years, the photo sharing website Flickr allowed its users to add their own text tags to each of their pictures, constructing flexible and easy metadata that made the pictures highly searchable. The success of Flickr and the influence of Delicious popularized the concept, and other social software websites—such as YouTube, Technorati, and Last.fm—also implemented tagging. In 2005, the Atom web syndication standard provided a "category" element for inserting subject categories into web feeds, and in 2007 Tim Bray proposed a "tag" URN. == Examples == === Within a blog === Many systems (and other web content management systems) allow authors to add free-form tags to a post, along with (or instead of) placing the post into a predetermined category. For example, a post may display that it has been tagged with baseball and tickets. Each of those tags is usually a web link leading to an index page listing all of the posts associated with that tag. The blog may have a sidebar listing all the tags in use on that blog, with each tag leading to an index page. To reclassify a post, an author edits its list of tags. All connections between posts are automatically tracked and updated by the blog software; there is no need to relocate the page within a complex hierarchy of categories. === Within application software === Some desktop applications and web applications feature their own tagging systems, such as email tagging in Gmail and Mozilla Thunderbird, bookmark tagging in Firefox, audio tagging in iTunes or Winamp, and photo tagging in various applications. Some of these applications display collections of tags as tag clouds. === Assigned to computer files === There are various systems for applying tags to the files in a computer's file system. In Apple's Mac System 7, released in 1991, users could assign one of seven editable colored labels (with editable names such as "Essential", "Hot", and "In Progress") to each file and folder. In later iterations of the Mac operating system ever since OS X 10.9 was released in 2013, users could assign multiple arbitrary tags as extended file attributes to any file or folder, and before that time the open-source OpenMeta standard provided similar tagging functionality for Mac OS X. Several semantic file systems that implement tags are available for the Linux kernel, including Tagsistant. Microsoft Windows allows users to set tags only on Microsoft Office documents and some kinds of picture files. Cross-platform file tagging standards include Extensible Metadata Platform (XMP), an ISO standard for embedding metadata into popular image, video and document file formats, such as JPEG and PDF, without breaking their readability by applications that do not support XMP. XMP largely supersedes the earlier IPTC Information Interchange Model. Exif is a standard that specifies the image and audio file formats used by digital cameras, including some metadata tags. TagSpaces is an open-source cross-platform application for tagging files; it inserts tags into the filename. === For an event === An official tag is a keyword adopted by events and conferences for participants to use in their web publications, such as blog entries, photos of the event, and presentation slides. Search engines can then index them to make relevant materials related to the event searchable in a uniform way. In this case, the tag is part of a controlled vocabulary. === In research === A researcher may work with a large collection of items (e.g. press quotes, a bibliography, images) in digital form. If he/she wishes to associate each with a small number of themes (e.g. to chapters of a book, or to sub-themes of the overall subject), then a group of tags for these themes can be attached to each of the items in
Read more →
Learning vector quantization

In computer science, learning vector quantization (LVQ) is a prototype-based supervised classification algorithm. LVQ is the supervised counterpart of vector quantization systems. LVQ can be understood as a special case of an artificial neural network, more precisely, it applies a winner-take-all Hebbian learning-based approach. It is a precursor to self-organizing maps (SOM) and related to neural gas and the k-nearest neighbor algorithm (k-NN). LVQ was invented by Teuvo Kohonen. == Definition == An LVQ system is represented by prototypes W = ( w ( i ) , . . . , w ( n ) ) {\displaystyle W=(w(i),...,w(n))} which are defined in the feature space of observed data. In winner-take-all training algorithms one determines, for each data point, the prototype which is closest to the input according to a given distance measure. The position of this so-called winner prototype is then adapted, i.e. the winner is moved closer if it correctly classifies the data point or moved away if it classifies the data point incorrectly. An advantage of LVQ is that it creates prototypes that are easy to interpret for experts in the respective application domain. LVQ systems can be applied to multi-class classification problems in a natural way. A key issue in LVQ is the choice of an appropriate measure of distance or similarity for training and classification. Recently, techniques have been developed which adapt a parameterized distance measure in the course of training the system, see e.g. (Schneider, Biehl, and Hammer, 2009) and references therein. LVQ can be a valuable aid in classifying text documents. == Algorithm == The algorithms are presented as in. Set up: Let the data be denoted by x i ∈ R D {\displaystyle x_{i}\in \mathbb {R} ^{D}} , and their corresponding labels by y i ∈ { 1 , 2 , … , C } {\displaystyle y_{i}\in \{1,2,\dots ,C\}} . The complete dataset is { ( x i , y i ) } i = 1 N {\displaystyle \{(x_{i},y_{i})\}_{i=1}^{N}} . The set of code vectors is w j ∈ R D {\displaystyle w_{j}\in \mathbb {R} ^{D}} . The learning rate at iteration step t {\displaystyle t} is denoted by α t {\displaystyle \alpha _{t}} . The hyperparameters w {\displaystyle w} and ϵ {\displaystyle \epsilon } are used by LVQ2 and LVQ3. The original paper suggests ϵ ∈ [ 0.1 , 0.5 ] {\displaystyle \epsilon \in [0.1,0.5]} and w ∈ [ 0.2 , 0.3 ] {\displaystyle w\in [0.2,0.3]} . === LVQ1 === Initialize several code vectors per label. Iterate until convergence criteria is reached. Sample a datum x i {\displaystyle x_{i}} , and find out the code vector w j {\displaystyle w_{j}} , such that x i {\displaystyle x_{i}} falls within the Voronoi cell of w j {\displaystyle w_{j}} . If its label y i {\displaystyle y_{i}} is the same as that of w j {\displaystyle w_{j}} , then w j ← w j + α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}+\alpha _{t}(x_{i}-w_{j})} , otherwise, w j ← w j − α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}-\alpha _{t}(x_{i}-w_{j})} . === LVQ2 === LVQ2 is the same as LVQ3, but with this sentence removed: "If w j {\displaystyle w_{j}} and w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have the same class, then w j ← w j − α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}-\alpha _{t}(x_{i}-w_{j})} and w k ← w k + α t ( x i − w k ) {\displaystyle w_{k}\leftarrow w_{k}+\alpha _{t}(x_{i}-w_{k})} .". If w j {\displaystyle w_{j}} and w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have the same class, then nothing happens. === LVQ3 === Initialize several code vectors per label. Iterate until convergence criteria is reached. Sample a datum x i {\displaystyle x_{i}} , and find out two code vectors w j , w k {\displaystyle w_{j},w_{k}} closest to it. Let d j := ‖ x i − w j ‖ , d k := ‖ x i − w k ‖ {\displaystyle d_{j}:=\|x_{i}-w_{j}\|,d_{k}:=\|x_{i}-w_{k}\|} . If min ( d j d k , d k d j ) > s {\displaystyle \min \left({\frac {d_{j}}{d_{k}}},{\frac {d_{k}}{d_{j}}}\right)>s} , where s = 1 − w 1 + w {\displaystyle s={\frac {1-w}{1+w}}} , then If w j {\displaystyle w_{j}} and x i {\displaystyle x_{i}} have the same class, and w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have different classes, then w j ← w j + α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}+\alpha _{t}(x_{i}-w_{j})} and w k ← w k − α t ( x i − w k ) {\displaystyle w_{k}\leftarrow w_{k}-\alpha _{t}(x_{i}-w_{k})} . If w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have the same class, and w j {\displaystyle w_{j}} and x i {\displaystyle x_{i}} have different classes, then w j ← w j − α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}-\alpha _{t}(x_{i}-w_{j})} and w k ← w k + α t ( x i − w k ) {\displaystyle w_{k}\leftarrow w_{k}+\alpha _{t}(x_{i}-w_{k})} . If w j {\displaystyle w_{j}} and w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have the same class, then w j ← w j − ϵ α t ( x i − w j ) {\displaystyle w_{j}\leftarrow w_{j}-\epsilon \alpha _{t}(x_{i}-w_{j})} and w k ← w k + ϵ α t ( x i − w k ) {\displaystyle w_{k}\leftarrow w_{k}+\epsilon \alpha _{t}(x_{i}-w_{k})} . If w k {\displaystyle w_{k}} and x i {\displaystyle x_{i}} have different classes, and w j {\displaystyle w_{j}} and x i {\displaystyle x_{i}} have different classes, then the original paper simply does not explain what happens in this case, but presumably nothing happens in this case. Otherwise, skip. Note that condition min ( d j d k , d k d j ) > s {\displaystyle \min \left({\frac {d_{j}}{d_{k}}},{\frac {d_{k}}{d_{j}}}\right)>s} , where s = 1 − w 1 + w {\displaystyle s={\frac {1-w}{1+w}}} , precisely means that the point x i {\displaystyle x_{i}} falls between two Apollonian spheres.
Read more →
Thinking Machines Lab

Thinking Machines Lab Inc. is an American artificial intelligence (AI) startup founded by Mira Murati, the former chief technology officer of OpenAI. The company was founded in February 2025, and by July had completed an early-stage funding round led by Andreessen Horowitz, raising $2 billion at a valuation of $12 billion overall from investors such as Nvidia, AMD, Cisco, and Jane Street. The company is based in San Francisco and structured as a public benefit corporation. == History == By its launch in February 2025, Thinking Machines Lab was reported to have hired about 30 researchers and engineers from competitors including OpenAI, Meta AI, and Mistral AI. Its founding team members include Barret Zoph, former OpenAI VP of Research (Post-Training), Lilian Weng, former OpenAI VP, and OpenAI cofounder John Schulman, who joined after a brief stint at the lab's competitor Anthropic. In January 2026, it was reported that Barret Zoph and Luke Metz, departed the startup to return to OpenAI. Other former OpenAI employees who have been hired include Jonathan Lachman and Andrew Tulloch (although Tulloch departed after getting recruited for Meta Superintelligence Labs). Thinking Machines Lab's advisers include Bob McGrew, previously OpenAI's chief research officer, and Alec Radford, who was a lead researcher for OpenAI. On October 1, 2025, it announced Tinker, an API for fine-tuning language models. Users would submit jobs through the API for fine-tuning one of the various open-weight models supported. The Lab would run the jobs on its internal clusters and training infrastructure. == Business structure == Thinking Machines Lab grants Mira Murati a deciding vote on board matters, weighted to provide her with a majority decision-making capability. Additionally, founding shareholders possess votes weighted 100 times greater than those of regular shareholders. In July 2025, Andreessen Horowitz was reported to have led the company's initial funding round, raising "about $2 billion at a valuation of $12 billion". The government of Albania (Murati's country of origin) was also included in this round, making a $10 million investment which required an amendment to the country's 2025 budget. == Partnership == In March 2026, Thinking Machines Lab announced a strategic partnership with NVIDIA involving an undisclosed investment and a multi-year agreement to deploy one gigawatt of Vera Rubin computing capacity.
Read more →
Interlacing (bitmaps)

In computing, interlacing (also known as interleaving) is a method of encoding a bitmap image such that a person who has partially received it sees a degraded copy of the entire image. When communicating over a slow communications link, this is often preferable to seeing a perfectly clear copy of one part of the image, as it helps the viewer decide more quickly whether to abort or continue the transmission. Interlacing is supported by the following formats, where it is optional: GIF interlacing stores the lines in the order 0 , 8 , 16 , … , ( 8 n ) , 4 , 12 , … , ( 8 n + 4 ) , 2 , 6 , 10 , 14 , … , ( 4 n + 2 ) , 1 , 3 , 5 , 7 , 9 , … , ( 2 n + 1 ) . {\displaystyle 0,8,16,\dots ,(8n),\ 4,12,\dots ,(8n+4),\ 2,6,10,14,\dots ,(4n+2),\ 1,3,5,7,9,\dots ,(2n+1).} PNG uses the Adam7 algorithm, which interlaces in both the vertical and horizontal direction. TGA uses two optional interlacing algorithms: Two-way: 0 , 2 , 4 , … , ( 2 n ) , 1 , 3 , … , ( 2 n + 1 ) , {\displaystyle 0,2,4,\dots ,(2n),\ 1,3,\dots ,(2n+1),} And four-way: 0 , 4 , 8 , … , ( 4 n ) , 1 , 5 , … , ( 4 n + 1 ) , 2 , 6 , … , ( 4 n + 2 ) , 3 , 7 , … , ( 4 n + 3 ) . {\displaystyle 0,4,8,\dots ,(4n),\ 1,5,\dots ,(4n+1),\ 2,6,\dots ,\ (4n+2),3,7,\dots ,(4n+3).} JPEG, JPEG 2000, and JPEG XR (actually using a frequency decomposition hierarchy rather than interlacing of pixel values) PGF (also using a frequency decomposition) Interlacing is a form of incremental decoding, because the image can be loaded incrementally. Another form of incremental decoding is progressive scan. In progressive scan the loaded image is decoded line for line, so instead of becoming incrementally clearer it becomes incrementally larger. The main difference between the interlace concept in bitmaps and in video is that even progressive bitmaps can be loaded over multiple frames. For example: Interlaced GIF is a GIF image that seems to arrive on your display like an image coming through a slowly opening Venetian blind. A fuzzy outline of an image is gradually replaced by seven successive waves of bit streams that fill in the missing lines until the image arrives at its full resolution. Interlaced graphics were once widely used in web design and before that in the distribution of graphics files over bulletin board systems and other low-speed communications methods. The practice is much less common today, as common broadband internet connections allow most images to be downloaded to the user's screen nearly instantaneously, and interlacing is usually an inefficient method of encoding images. Interlacing has been criticized because it may not be clear to viewers when the image has finished rendering, unlike non-interlaced rendering, where progress is apparent (remaining data appears as blank). Also, the benefits of interlacing to those on low-speed connections may be outweighed by having to download a larger file, as interlaced images typically do not compress as well.
Read more →
Infer.NET

Infer.NET is a free and open source .NET software library for machine learning. It supports running Bayesian inference in graphical models and can also be used for probabilistic programming. == Overview == Infer.NET follows a model-based approach and is used to solve different kinds of machine learning problems including standard problems like classification, recommendation or clustering, customized solutions and domain-specific problems. The framework is used in various different domains such as bioinformatics, epidemiology, computer vision, and information retrieval. Development of the framework was started by a team at Microsoft's research centre in Cambridge, UK in 2004. It was first released for academic use in 2008 and later open sourced in 2018. In 2013, Microsoft was awarded the USPTO's Patents for Humanity Award in Information Technology category for Infer.NET and the work in advanced machine learning techniques. Infer.NET is used internally at Microsoft as the machine learning engine in some of their products such as Office, Azure, and Xbox. The source code is licensed under MIT License and available on GitHub. It is also available as NuGet package.
Read more →
KataGo

KataGo is a free and open-source computer Go program, capable of defeating top-level human players. First released on 27 February 2019, it is developed by David Wu, who also developed the Arimaa playing program bot_Sharp which defeated three top human players to win the Arimaa AI Challenge in 2015. KataGo's first release was trained by David Wu using resources provided by his employer Jane Street Capital, but it is now trained by a distributed effort. Members of the computer Go community provide computing resources by running the client, which generates self-play games and rating games, and submits them to a server. The self-play games are used to train newer networks and the rating games to evaluate the networks' relative strengths. KataGo supports the Go Text Protocol, with various extensions, thus making it compatible with popular GUIs such as Lizzie. As an alternative, it also implements a custom "analysis engine" protocol, which is used by the KaTrain GUI, among others. KataGo is widely used by strong human go players, including the South Korean national team, for training purposes. KataGo is also used as the default analysis engine in the online Go website AI Sensei, as well as OGS (the Online Go Server). == Technology == Based on techniques used by DeepMind's AlphaGo Zero, KataGo implements Monte Carlo tree search with a convolutional neural network providing position evaluation and policy guidance. Compared to AlphaGo, KataGo introduces many refinements that enable it to learn faster and play more strongly. Notable features of KataGo that are absent in many other Go-playing programs include score estimation; support for small boards, rectangular boards, and large boards; arbitrary values of komi and handicaps; and the ability to use various Go rulesets and adjust its play and evaluation for the small differences between them. === Network === The network used in KataGo are ResNets with pre-activation. While AlphaGo Zero has only game board history as input features (as it was designed as a general architecture for board games, subsequently becoming AlphaZero), the input to the network contains additional features designed by hand specifically for playing Go. These features include liberties, komi parity, pass-alive, and ladders. The trunk is essentially the same as in AlphaGo Zero, but with global pooling layers added to allow the network to be conditioned on global context such as ko fights. This is similar to the Squeeze-and-Excitation Network. The network has two heads: a policy head and a value head. The policy and value heads are mostly the same as in AlphaGo Zero, but both heads have auxiliary subheads to provide auxiliary loss signal for faster training: Policy head: predicts policy for the current player's move this turn, and the opponent player's move in the next turn. A policy Each is a logit array of size 19 × 19 + 1 {\displaystyle 19\times 19+1} , representing the logit of making a move in one of the points, plus the logit of passing. Value head: predicts game outcome, expected score difference, expected board ownership, etc. The network is described in detail in Appendix A of the report. The code base switched from using TensorFlow to PyTorch in version 1.12. === Training === Let its trunk have b {\displaystyle b} residual blocks and c {\displaystyle c} channels. During its first training run, multiple networks were trained with increasing ( b , c ) {\displaystyle (b,c)} . It took 19 days using a maximum of 28 Nvidia V100 GPUs at 4.2 million games. After the first training run, training became a distributed project run by volunteers, with increasing network sizes. As of August 2024, it has reached b28c512 (28 blocks, 512 channels). == Adversarial attacks == In 2022, KataGo was used as the target for adversarial attack research, designed to demonstrate the "surprising failure modes" of AI systems. The researchers were able to trick KataGo into ending the game prematurely. Adversarial training improves defense against adversarial attacks, though not perfectly.
Read more →
Project Maven

Project Maven (officially Algorithmic Warfare Cross Functional Team) is a United States Department of Defense initiative launched in 2017 to accelerate the adoption of machine learning and data integration across U.S. military intelligence workflows, specifically in intelligence, surveillance, target acquisition, and reconnaissance as well as in geospatial intelligence. It initially focused on applying computer vision for processing images and videos for intelligence purposes. Currently, the program operates under the National Geospatial-Intelligence Agency (NGA) and encompasses multiple applications across the Department of Defense spanning military operation targeting support, data integration and visualization for analysts, and training machine learning models on labeled datasets of military assets and infrastructure. It integrates data from drones, satellites, and other sensors to flag potential targets, present findings to human analysts, and relay their decisions to operational systems. The program originated under Deputy Secretary Robert O. Work after he raised concerns about China's advances in defense applications of artificial intelligence. Project leaders, Colonel Drew Cukor, USMC, and Lt. Gen. Jack Shanahan, framed the program as human-in-the-loop decision support inside the Department of Defense rather than as an autonomous weapons platform. Contractors supporting Maven have included Google, which withdrew in 2018 after internal protests, and follow-on integrators such as Palantir, Anduril, Amazon Web Services, and Anthropic (withdrew in 2026). The Pentagon credits Maven with providing 2024 targeting support for U.S. airstrikes in Iraq, Syria, and Yemen, along with locating hostile maritime assets in the Red Sea. == Administrative history == Initially, the effort was led by Robert O. Work who was concerned about China's military use of the emerging technology. Reportedly, Pentagon development stops short of acting as an AI weapons system capable of firing on self-designated targets. The project was established in a memo by the U.S. Deputy Secretary of Defense on 26 April 2017 proposing an "Algorithmic Warfare Cross-Functional Team". With the help of Defense Innovation Unit, the project obtained the support of top talents in AI outside of the traditional defense contracting base. It was initially funded for $70 million. Jack Shanahan was the director of the project during April 2017 to December 2018. At the second Defense One Tech Summit in July 2017, Cukor said that the investment in a "deliberate workflow process" was funded by the Department [of Defense] through its "rapid acquisition authorities" for about "the next 36 months". In the defense industry, the standard procedure for the military to acquire hardware is by way of research, development, test, and evaluation (RDT&E), followed by production and sustainment. In 2017, acquiring software was done in the same way as hardware. This created a problem, since software is constantly updated. Project Maven procured software using Broad Agency Announcements, a flexible contracting vehicle that categorized software as consistently RDT&E, allowing constant updating. Another issue was that the government usually acquired the intellectual property (IP) for procured software, and with the project, only parts of the IP of the software was acquired. Cukor used the principle of "platform IP belongs to the vendor, configurations on top are the customer's". For example, Palantir retained IP to their core platform, while the government obtained the IP to Maven-specific logic configured on top of it. According to US Air Force Lt. Gen. Jack Shanahan in November 2017, it is "designed to be that pilot project, that pathfinder, that spark that kindles the flame front of artificial intelligence across the rest of the [Defense] Department". Its chief, U.S. Marine Corps Col. Drew Cukor, said: "People and computers will work symbiotically to increase the ability of weapon systems to detect objects." Project Maven has been noted by allies, such as Australia's Ian Langford, for the ability to identify adversaries by harvesting data from sensors on UAVs and satellites. As of 2017 December, 150,000 images had been manually labelled to establish the first training data sets, and it was projected to reach one million by January 2018. Project Maven was funded for $221 million in fiscal 2020. In 2020, the House and Senate conferees on the National Defense Authorization Act for Fiscal Year 2021, agreed to the Senate's recommendation to fund the Pentagon's $250 million request for Project Maven. At the GEOINT Symposium of 2022, it was announced that Project Maven was transferred from the Office of the Under Secretary of Defense for Intelligence and Security to the NGA, under President Biden’s proposed budget for Fiscal Year 2023. It became a Program of Record on 2023 November 7. Frank "Trey" Whitworth, vice admiral, was the director of NGA from June 2022 to November 2025. Whitworth was initially skeptical of the program, suspecting it was incautious about the targeting principles, but later regarded it as "important work". As of 2024, the project is jointly administered by the NGA and the CDAO, and its director is Rachel Martin. Before 2025, Biden appointees within CDAO had held back AI development for safety and reliability concerns, though as of 2025, this has stopped. As of 2024, Maven provided the cloud infrastructure, software capabilities, and AI for CDAO's Combined Joint All-Domain Command and Control initiatives. As of summer 2025, there were eight Maven initiatives. Of these, five were in the NGA, including analyzing drone feeds and satellite imagery. On 18 September 2025, the UK government announced a new partnership with Palantir to develop AI-powered military capabilities for decision-making and targeting, identifying opportunities worth up to £750 million over five years. On 25 March 2025, the NATO Communications and Information Agency and Palantir finalized the acquisition of the Palantir Maven Smart System NATO (MSS NATO) for employment within NATO's Allied Command Operations. It was planned to be used within 30 days of acquisition. In a letter to Pentagon on 9 March 2026, Steve Feinberg stated that Project Maven will become an official program of record by September 2026, the close of the current fiscal year. The project would transfer from the NGA to the CDAO within 30 days. Future contracting with Palantir would be handled by the US Army. In 2026-03, it was announced that the US Army Combined Arms Command would integrate Maven into its training. == Technology == Project Maven uses machine learning algorithms to analyze and fuse vast amounts of surveillance data from multiple sources made possible through data integration using Palantir Technologies. The data sources include photographs, satellite imagery, geolocation data (IP address, geotag, metadata, etc) from communications intercepts, infrared sensors, synthetic-aperture radar, and more. The system is mainly used for assisting analysts in intelligence, surveillance, target acquisition, and reconnaissance. Machine learning systems, including object recognition systems, process the data and identify potential targets, such as enemy tanks or location of new military facility. The training dataset included at least 4 million images of military objects such as warships, labelled by humans. The user interface is called Maven Smart System. It could display information such as aircraft movements, logistics, locations of key personnel, locations on the no-strike list, ships, etc. Yellow-outlined boxes show potential targets. Blue-outlined boxes show friendly forces or no-strike zones. It could also transmit, directly to weapons, a human decision to fire weapons. Internal documentation referred to "Maven ATR: automatic target recognition". Initially the project focused on applications of computer vision. The project's leaders were particularly impressed by model performance on ImageNet. As of 2018, the purpose of the system was AI-enabled analysis of full-motion video. In 2022 it expanded to combatant commands under the AI and Data Acceleration Initiative. In 2022, it was reported that the project expanded to non-image data, including captured enemy material, maritime intelligence, and publicly available information. In 2024, it was stated that Maven's key technical contribution was data management: Maven standardizes heterogeneous data through an ontology layer so data can be fused, exchanged across cloud and edge systems, and used by multiple applications. The system was presented as a broader data-centric warfighting system that feeds apps for planning, preparing, and executing operations. In 2024, the Broad Area Surveillance-Targeting (BAS-T) is a part of Maven. The system detects objects in images and uses data fusion to produce a common operational picture containing "priority based, in-depth assessment of the enemy systems pre
Read more →
Learning to rank

Learning to rank (LTR) or machine-learned ranking (MLR) is the application of machine learning, often supervised, semi-supervised or reinforcement learning, in the construction of ranking models for information retrieval and recommender systems. Training data may, for example, consist of lists of items with some partial order specified between items in each list. This order is typically induced by giving a numerical or ordinal score or a binary judgment (e.g. "relevant" or "not relevant") for each item. The goal of constructing the ranking model is to rank new, unseen lists in a similar way to rankings in the training data. == Applications == === In information retrieval === Ranking is a central part of many information retrieval problems, such as document retrieval, collaborative filtering, sentiment analysis, and online advertising. A possible architecture of a machine-learned search engine is shown in the accompanying figure. Training data consists of queries and documents matching them together with the relevance degree of each match. It may be prepared manually by human assessors (or raters, as Google calls them), who check results for some queries and determine relevance of each result. It is not feasible to check the relevance of all documents, and so typically a technique called pooling is used — only the top few documents, retrieved by some existing ranking models are checked. This technique may introduce selection bias. Alternatively, training data may be derived automatically by analyzing clickthrough logs (i.e. search results which got clicks from users), query chains, or such search engines' features as Google's (since-replaced) SearchWiki. Clickthrough logs can be biased by the tendency of users to click on the top search results on the assumption that they are already well-ranked. Training data is used by a learning algorithm to produce a ranking model which computes the relevance of documents for actual queries. Typically, users expect a search query to complete in a short time (such as a few hundred milliseconds for web search), which makes it impossible to evaluate a complex ranking model on each document in the corpus, and so a two-phase scheme is used. First, a small number of potentially relevant documents are identified using simpler retrieval models which permit fast query evaluation, such as the vector space model, Boolean model, weighted AND, or BM25. This phase is called top- k {\displaystyle k} document retrieval and many heuristics were proposed in the literature to accelerate it, such as using a document's static quality score and tiered indexes. In the second phase, a more accurate but computationally expensive machine-learned model is used to re-rank these documents. === In other areas === Learning to rank algorithms have been applied in areas other than information retrieval: In machine translation for ranking a set of hypothesized translations; In computational biology for ranking candidate 3-D structures in protein structure prediction problems; In recommender systems for identifying a ranked list of related news articles to recommend to a user after he or she has read a current news article. == Feature vectors == For the convenience of MLR algorithms, query-document pairs are usually represented by numerical vectors, which are called feature vectors. Such an approach is sometimes called bag of features and is analogous to the bag of words model and vector space model used in information retrieval for representation of documents. Components of such vectors are called features, factors or ranking signals. They may be divided into three groups (features from document retrieval are shown as examples): Query-independent or static features — those features, which depend only on the document, but not on the query. For example, PageRank or document's length. Such features can be precomputed in off-line mode during indexing. They may be used to compute document's static quality score (or static rank), which is often used to speed up search query evaluation. Query-dependent or dynamic features — those features, which depend both on the contents of the document and the query, such as TF-IDF score or other non-machine-learned ranking functions. Query-level features or query features, which depend only on the query. For example, the number of words in a query. Some examples of features, which were used in the well-known LETOR dataset: TF, TF-IDF, BM25, and language modeling scores of document's zones (title, body, anchors text, URL) for a given query; Lengths and IDF sums of document's zones; Document's PageRank, HITS ranks and their variants. Selecting and designing good features is an important area in machine learning, which is called feature engineering. == Evaluation measures == There are several measures (metrics) which are commonly used to judge how well an algorithm is doing on training data and to compare the performance of different MLR algorithms. Often a learning-to-rank problem is reformulated as an optimization problem with respect to one of these metrics. Examples of ranking quality measures: Mean average precision (MAP); DCG and NDCG; Precision@n, NDCG@n, where "@n" denotes that the metrics are evaluated only on top n documents; Mean reciprocal rank; Kendall's tau; Spearman's rho. DCG and its normalized variant NDCG are usually preferred in academic research when multiple levels of relevance are used. Other metrics such as MAP, MRR and precision, are defined only for binary judgments. Recently, there have been proposed several new evaluation metrics which claim to model user's satisfaction with search results better than the DCG metric: Expected reciprocal rank (ERR); Yandex's pfound. Both of these metrics are based on the assumption that the user is more likely to stop looking at search results after examining a more relevant document, than after a less relevant document. == Approaches == Learning to Rank approaches are often categorized using one of three approaches: pointwise (where individual documents are ranked), pairwise (where pairs of documents are ranked into a relative order), and listwise (where an entire list of documents are ordered). Tie-Yan Liu of Microsoft Research Asia has analyzed existing algorithms for learning to rank problems in his book Learning to Rank for Information Retrieval. He categorized them into three groups by their input spaces, output spaces, hypothesis spaces (the core function of the model) and loss functions: the pointwise, pairwise, and listwise approach. In practice, listwise approaches often outperform pairwise approaches and pointwise approaches. This statement was further supported by a large scale experiment on the performance of different learning-to-rank methods on a large collection of benchmark data sets. In this section, without further notice, x {\displaystyle x} denotes an object to be evaluated, for example, a document or an image, f ( x ) {\displaystyle f(x)} denotes a single-value hypothesis, h ( ⋅ ) {\displaystyle h(\cdot )} denotes a bi-variate or multi-variate function and L ( ⋅ ) {\displaystyle L(\cdot )} denotes the loss function. === Pointwise approach === In this case, it is assumed that each query-document pair in the training data has a numerical or ordinal score. Then the learning-to-rank problem can be approximated by a regression problem — given a single query-document pair, predict its score. Formally speaking, the pointwise approach aims at learning a function f ( x ) {\displaystyle f(x)} predicting the real-value or ordinal score of a document x {\displaystyle x} using the loss function L ( f ; x j , y j ) {\displaystyle L(f;x_{j},y_{j})} . A number of existing supervised machine learning algorithms can be readily used for this purpose. Ordinal regression and classification algorithms can also be used in pointwise approach when they are used to predict the score of a single query-document pair, and it takes a small, finite number of values. === Pairwise approach === In this case, the learning-to-rank problem is approximated by a classification problem — learning a binary classifier h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} that can tell which document is better in a given pair of documents. The classifier shall take two documents as its input and the goal is to minimize a loss function L ( h ; x u , x v , y u , v ) {\displaystyle L(h;x_{u},x_{v},y_{u,v})} . The loss function typically reflects the number and magnitude of inversions in the induced ranking. In many cases, the binary classifier h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} is implemented with a scoring function f ( x ) {\displaystyle f(x)} . As an example, RankNet adapts a probability model and defines h ( x u , x v ) {\displaystyle h(x_{u},x_{v})} as the estimated probability of the document x u {\displaystyle x_{u}} has higher quality than x v {\displaystyle x_{v}} : P u , v ( f ) = CDF ( f ( x u ) − f ( x v ) ) , {\displaystyle P_{u,v}(f)={\text{CDF}
Read more →
Catastrophic interference

Catastrophic interference, also known as catastrophic forgetting, is the tendency of an artificial neural network to abruptly and drastically forget previously learned information upon learning new information. Neural networks are an important part of the connectionist approach to cognitive science. The issue of catastrophic interference when modeling human memory with connectionist models was originally brought to the attention of the scientific community by research from McCloskey and Cohen (1989), and Ratcliff (1990). It is a radical manifestation of the 'sensitivity-stability' dilemma or the 'stability-plasticity' dilemma. Specifically, these problems refer to the challenge of making an artificial neural network that is sensitive to, but not disrupted by, new information. Lookup tables and connectionist networks lie on the opposite sides of the stability plasticity spectrum. The former remains completely stable in the presence of new information but lacks the ability to generalize, i.e. infer general principles, from new inputs. On the other hand, connectionist networks like the standard backpropagation network can generalize to unseen inputs, but they are sensitive to new information. Backpropagation models can be analogized to human memory insofar as they have a similar ability to generalize, but these networks often exhibit less stability than human memory. Notably, these backpropagation networks are susceptible to catastrophic interference. This is an issue when modelling human memory, because unlike these networks, humans typically do not show catastrophic forgetting. == Discovery == The term catastrophic interference was originally coined by McCloskey and Cohen (1989) but was also brought to the attention of the scientific community by research from Ratcliff (1990). === The Sequential Learning Problem: McCloskey and Cohen (1989) === McCloskey and Cohen (1989) noted the problem of catastrophic interference during two different experiments with backpropagation neural network modelling. Experiment 1: Learning the ones and twos addition facts In their first experiment they trained a standard backpropagation neural network on a single training set consisting of 17 single-digit ones problems (i.e., 1 + 1 through 9 + 1, and 1 + 2 through 1 + 9) until the network could represent and respond properly to all of them. The error between the actual output and the desired output steadily declined across training sessions, which reflected that the network learned to represent the target outputs better across trials. Next, they trained the network on a single training set consisting of 17 single-digit twos problems (i.e., 2 + 1 through 2 + 9, and 1 + 2 through 9 + 2) until the network could represent, respond properly to all of them. They noted that their procedure was similar to how a child would learn their addition facts. Following each learning trial on the twos facts, the network was tested for its knowledge on both the ones and twos addition facts. Like the ones facts, the twos facts were readily learned by the network. However, McCloskey and Cohen noted the network was no longer able to properly answer the ones addition problems even after one learning trial of the twos addition problems. The output pattern produced in response to the ones facts often resembled an output pattern for an incorrect number more closely than the output pattern for a correct number. This is considered to be a drastic amount of error. Furthermore, the problems 2+1 and 1+2, which were included in both training sets, even showed dramatic disruption during the first learning trials of the twos facts. Experiment 2: Replication of Barnes and Underwood (1959) study In their second connectionist model, McCloskey and Cohen attempted to replicate the study on retroactive interference in humans by Barnes and Underwood (1959). They trained the model on A-B and A-C lists and used a context pattern in the input vector (input pattern), to differentiate between the lists. Specifically the network was trained to respond with the right B response when shown the A stimulus and A-B context pattern and to respond with the correct C response when shown the A stimulus and the A-C context pattern. When the model was trained concurrently on the A-B and A-C items then the network readily learned all of the associations correctly. In sequential training the A-B list was trained first, followed by the A-C list. After each presentation of the A-C list, performance was measured for both the A-B and A-C lists. They found that the amount of training on the A-C list in Barnes and Underwood study that lead to 50% correct responses, lead to nearly 0% correct responses by the backpropagation network. Furthermore, they found that the network tended to show responses that looked like the C response pattern when the network was prompted to give the B response pattern. This indicated that the A-C list apparently had overwritten the A-B list. This could be likened to learning the word dog, followed by learning the word stool and then finding that you think of the word stool when presented with the word dog. McCloskey and Cohen tried to reduce interference through a number of manipulations including changing the number of hidden units, changing the value of the learning rate parameter, overtraining on the A-B list, freezing certain connection weights, changing target values 0 and 1 instead 0.1 and 0.9. However, none of these manipulations satisfactorily reduced the catastrophic interference exhibited by the networks. Overall, McCloskey and Cohen (1989) concluded that: at least some interference will occur whenever new learning alters the weights involved in representing old learning the greater the amount of new learning, the greater the disruption in old knowledge interference was catastrophic in the backpropagation networks when learning was sequential but not concurrent === Constraints Imposed by Learning and Forgetting Functions: Ratcliff (1990) === Ratcliff (1990) used multiple sets of backpropagation models applied to standard recognition memory procedures, in which the items were sequentially learned. After inspecting the recognition performance models he found two major problems: Well-learned information was catastrophically forgotten as new information was learned in both small and large backpropagation networks. Even one learning trial with new information resulted in a significant loss of the old information, paralleling the findings of McCloskey and Cohen (1989). Ratcliff also found that the resulting outputs were often a blend of the previous input and the new input. In larger networks, items learned in groups (e.g. AB then CD) were more resistant to forgetting than were items learned singly (e.g. A then B then C...). However, the forgetting for items learned in groups was still large. Adding new hidden units to the network did not reduce interference. Discrimination between the studied items and previously unseen items decreased as the network learned more. This finding contradicts studies on human memory, which indicated that discrimination increases with learning. Ratcliff attempted to alleviate this problem by adding 'response nodes' that would selectively respond to old and new inputs. However, this method did not work as these response nodes would become active for all inputs. A model which used a context pattern also failed to increase discrimination between new and old items. == Proposed solutions == The main cause of catastrophic interference seems to be overlap in the representations at the hidden layer of distributed neural networks. In a distributed representation, each input tends to create changes in the weights of many of the nodes. Catastrophic forgetting occurs because when many of the weights where "knowledge is stored" are changed, it is unlikely for prior knowledge to be kept intact. During sequential learning, the inputs become mixed, with the new inputs being superimposed on top of the old ones. Another way to conceptualize this is by visualizing learning as a movement through a weight space. This weight space can be likened to a spatial representation of all of the possible combinations of weights that the network could possess. When a network first learns to represent a set of patterns, it finds a point in the weight space that allows it to recognize all of those patterns. However, when the network then learns a new set of patterns, it will move to a place in the weight space for which the only concern is the recognition of the new patterns. To recognize both sets of patterns, the network must find a place in the weight space suitable for recognizing both the new and the old patterns. Below are a number of techniques which have empirical support in successfully reducing catastrophic interference in backpropagation neural networks: === Orthogonality === Many of the early techniques in reducing representational overlap involved making either the input vecto
Read more →
Emospark

EmoSpark is an artificial intelligence console created in London, United Kingdom by Patrick Levy-Rosenthal. The device uses facial recognition and language analysis to evaluate human emotion and convey responsive content according to the emotion. The console measures 90 mm x 90 mm x 90 mm and is cube shaped. It operates on an "Emotional Processing Unit", an emotion chip developed by Emoshape Inc. that enables the system to create emotional profile graphs of its surroundings. The emotional processing unit is a patent pending technology that is said to create synthesised emotional responses in machines. EmoSpark was funded through an Indiegogo campaign which aimed to raise $200,000. == Product overview == EmoSpark was created by French inventor Patrick Levy-Rosenthal, as an emotionally intelligent artificial life unit for the home that can interact with people. It is powered by Android and can communicate with users through typed input from a computer, tablet, smartphone or TV as well as through spoken commands. The EmoSpark's features are categorized into two types: functional and emotional. EmoSpark is said to have the ability to perform practical software-based tasks. Through the smartphone interface, it is able to gauge a person’s emotions and is reported to have a conversational library of over 2 million sentences. The face-tracking technology identifies users likes and dislikes to categorize their emotional responses to stimuli such as videos and music. The device has an emotional spectrum that is composed of eight emotions which are surprise, sadness, joy, trust, fear, disgust, anger and anticipation. EmoSpark monitors a person's facial expressions and emotions through images from an external camera, which are then processed through an emotion text analysis and content analysis. The New Scientist reported that EmoSpark had the ability to work on the best way to cheer up its users, emotionally. === Connectivity === EmoSpark is able to connect to Facebook and YouTube to present users with content designed to improve their mood, or to Wikipedia for collaborative knowledge that can be shared when users ask questions of it. Through Android OS, EmoSpark is able to be customized with Google Play store apps. The cube is expected to develop its own personality based on the communications it has had with the people using it. == EmoShape == The Emotion Chip (EPU) used in the cube is created by the US company Emoshape Inc, founded by Levy-Rosenthal. EmoShape Ltd (UK) was the company that developed EmoSpark cube. Patrick Levy-Rosenthal also received the IST Prize in 2005 from the European Council for Applied Science, Technology and Engineering.
Read more →