AI Detector Zero

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

• 

  Film recorder

  A film recorder is a graphical output device for transferring images to photographic film from a digital source. In a typical film recorder, an image is passed from a host computer to a mechanism to expose film through a variety of methods, historically by direct photography of a high-resolution cathode-ray tube (CRT) display. The exposed film can then be developed using conventional developing techniques, and displayed with a slide or motion picture projector. The use of film recorders predates the current use of digital projectors, which eliminate the time and cost involved in the intermediate step of transferring computer images to film stock, instead directly displaying the image signal from a computer. Motion picture film scanners are the opposite of film recorders, copying content from film stock to a computer system. Film recorders can be thought of as modern versions of kinescopes. == Design == === Operation === All film recorders typically work in the same manner. The image is fed from a host computer as a raster stream over a digital interface. A film recorder exposes film through various mechanisms; flying spot (early recorders); photographing a high resolution video monitor; electron beam recorder (Sony HDVS); a CRT scanning dot (Celco); focused beam of light from a light valve technology (LVT) recorder; a scanning laser beam (Arrilaser); or recently, full-frame LCD array chips. For color image recording on a CRT film recorder, the red, green, and blue channels are sequentially displayed on a single gray scale CRT, and exposed to the same piece of film as a multiple exposure through a filter of the appropriate color. This approach yields better resolution and color quality than possible with a tri-phosphor color CRT. The three filters are usually mounted on a motor-driven wheel. The filter wheel, as well as the camera's shutter, aperture, and film motion mechanism are usually controlled by the recorder's electronics and/or the driving software. CRT film recorders are further divided into analog and digital types. The analog film recorder uses the native video signal from the computer, while the digital type uses a separate display board in the computer to produce a digital signal for a display in the recorder. Digital CRT recorders provide a higher resolution at a higher cost compared to analog recorders due to the additional specialized hardware. Typical resolutions for digital recorders were quoted as 2K and 4K, referring to 2048×1366 and 4096×2732 pixels, respectively, while analog recorders provided a resolution of 640×428 pixels in comparison. Higher-quality LVT film recorders use a focused beam of light to write the image directly onto a film loaded spinning drum, one pixel at a time. In one example, the light valve was a liquid-crystal shutter, the light beam was steered with a lens, and text was printed using a pre-cut optical mask. The LVT will record pixel beyond grain. Some machines can burn 120-res or 120 lines per millimeter. The LVT is basically a reverse drum scanner. The exposed film is developed and printed by regular photographic chemical processing. === Formats === Film recorders are available for a variety of film types and formats. The 35 mm negative film and transparencies are popular because they can be processed by any photo shop. Single-image 4×5 film and 8×10 are often used for high-quality, large format printing. Some models have detachable film holders to handle multiple formats with the same camera or with Polaroid backs to provide on-site review of output before exposing film. == Uses == Film recorders are used in digital printing to generate master negatives for offset and other bulk printing processes. For preview, archiving, and small-volume reproduction, film recorders have been rendered obsolete by modern printers that produce photographic-quality hardcopies directly on plain paper. They are also used to produce the master copies of movies that use computer animation or other special effects based on digital image processing. However, most cinemas nowadays use Digital Cinema Packages on hard drives instead of film stock. === Computer graphics === Film recorders were among the earliest computer graphics output devices; for example, the IBM 740 CRT Recorder was announced in 1954. Film recorders were also commonly used to produce slides for slide projectors; but this need is now largely met by video projectors that project images directly from a computer to a screen. The terms "slide" and "slide deck" are still commonly used in presentation programs. === Current uses === Currently, film recorders are primarily used in the motion picture film-out process for the ever increasing amount of digital intermediate work being done. Although significant advances in large venue video projection alleviates the need to output to film, there remains a deadlock between the motion picture studios and theater owners over who should pay for the cost of these very costly projection systems. This, combined with the increase in international and independent film production, will keep the demand for film recording steady for at least a decade. == Key manufacturers == Traditional film recorder manufacturers have all but vanished from the scene or have evolved their product lines to cater to the motion picture industry. Dicomed was one such early provider of digital color film recorders. Polaroid, Management Graphics, Inc, MacDonald-Detwiler, Information International, Inc., and Agfa were other producers of film recorders. Arri is the only current major manufacturer of film recorders. Kodak Lightning I film recorder. One of the first laser recorders. Needed an engineering staff to set up. Kodak Lightning II film recorder used both gas and diode laser to record on to film. The last LVT machines produced by Kodak / Durst-Dice stopped production in 2002. There are no LVT film recorders currently being produced. LVT Saturn 1010 uses a LED exposure (RGB) to 8"x10" film at 1000-3000ppi. LUX Laser Cinema Recorder from Autologic/Information International in Thousand Oaks, California. Sales end in March 2000. Used on the 1997 film “Titanic”. Arri produces the Arrilaser line of laser-based motion picture film recorders. MGI produced the Solitaire line of CRT-based motion picture film recorders. Matrix, originally ImaPRO, a branch of Agfa Division, produced the QCR line of CRT-based motion picture film recorders. CCG, formerly Agfa film recorders, has been a steady manufacturer of film recorders based in Germany. In 2004 CCG introduced Definity, a motion picture film recorder utilizing LCD technology. In 2010 CCG introduced the first full LED LCD film recorder as a new step in film recording. Cinevator was made by Cinevation AS, in Drammen, Norway. The Cinevator was a real-time digital film recorder. It could record IN, IP and prints with and without sound Oxberry produced the Model 3100 film recorder camera system, with interchangeable pin-registered movements (shuttles) for 35 mm (full frame/Silent, 1.33:1) and 16 mm (regular 16, "2R"), and others have adapted the Oxberry movements for CinemaScope, 1.85:1, 1.75:1, 1.66:1, as well as Academy/Sound (1.37:1) in 35 mm and Super-16 in 16 mm ("1R"). For instance, the "Solitaire" and numerous others employed the Oxberry 3100 camera system. == History == Before video tape recorders or VTRs were invented, TV shows were either broadcast live or recorded to film for later showing, using the kinescope process. In 1967, CBS Laboratories introduced the Electronic Video Recording format, which used video and telecined-to-video film sources, which were then recorded with an electron-beam recorder at CBS' EVR mastering plant at the time to 35mm film stock in a rank of 4 strips on the film, which was then slit down to 4 8.75 mm (0.344 in) film copies, for playback in an EVR player. All types of CRT recorders were (and still are) used for film recording. Some early examples used for computer-output recording were the 1954 IBM 740 CRT Recorder, and the 1962 Stromberg-Carlson SC-4020, the latter using a Charactron CRT for text and vector graphic output to either 16 mm motion picture film, 16 mm microfilm, or hard-copy paper output. Later 1970 and 80s-era recording to B&W (and color, with 3 separate exposures for red, green, and blue)) 16 mm film was done with an EBR (Electron Beam Recorder), the most prominent examples made by 3M), for both video and COM (Computer Output Microfilm) applications. Image Transform in Universal City, California used specially modified 3M EBR film recorders that could perform color film-out recording on 16 mm by exposing three 16 mm frames in a row (one red, one green and one blue). The film was then printed to color 16 mm or 35 mm film. The video fed to the recorder could either be NTSC, PAL or SECAM. Later, Image Transform used specially modified VTRs to record 24 frame for their "Image Vision" system. The modified 1 inch type B videotape VTRs would record

  Read more →
• 

  Anna Becker

  Anna Becker is an Israeli researcher known in the field of artificial intelligence and computer science within the financial field. == Early life and education == Becker was born in Russia and immigrated to Israel at 16 after graduating from a school in Moscow. At 17, she began her studies at Technion – Israel Institute of Technology. During her master's degree in computer science, she taught first-year students of the same course, and at 27, Becker completed her PhD in Computer Science and Artificial Intelligence. == Career == While pursuing her PhD, Becker resolved an NP-complete approximation algorithm that had been unresolved for over twenty years. This made her a recognized scholar in the field. After completing her PhD, she developed an approximation technique by a factor of two. This technique is widely used today in operating systems, database systems, and VLSI chip designs. She then founded and sold Strategy Runner, a fintech software. After this, she founded EndoTech, an algorithmic trading platform based on artificial intelligence and machine learning. EndoTech's trading strategies have been operating in live cryptocurrency markets since 2017. The platform's BTC Alpha strategy has reported an average annual return of 163% on fixed capital over eight years of live operation, with a maximum drawdown of 14% and a trade accuracy rate of approximately 83%. In 2026, EndoTech entered a partnership with Bit1 Exchange to make its BTC Alpha and ETH Alpha copy trading strategies accessible to retail investors with no minimum deposit requirement, through a full-custody model in which user funds remain in their own exchange wallets at all times.As of 2023, Becker is working on Fianchetto Fund, an AI-based investing analysis platform. Becker has also co-authored a book on Bayesian networks, which has been published widely in the field of computer science and artificial intelligence.

  Read more →
• 

  Symbolic regression

  Symbolic regression (SR) is a type of regression analysis that searches the space of mathematical expressions to find the model that best fits a given dataset, both in terms of accuracy and simplicity. No particular model is provided as a starting point for symbolic regression. Instead, initial expressions are formed by randomly combining mathematical building blocks such as mathematical operators, analytic functions, constants, and state variables. Usually, a subset of these primitives will be specified by the person operating it, but that's not a requirement of the technique. The symbolic regression problem for mathematical functions has been tackled with a variety of methods, including recombining equations most commonly using genetic programming, as well as more recent methods utilizing Bayesian methods and neural networks. Another non-classical alternative method to SR is called Universal Functions Originator (UFO), which has a different mechanism, search-space, and building strategy. Further methods such as Exact Learning attempt to transform the fitting problem into a moments problem in a natural function space, usually built around generalizations of the Meijer-G function. By not requiring a priori specification of a model, symbolic regression isn't affected by human bias, or unknown gaps in domain knowledge. It attempts to uncover the intrinsic relationships of the dataset, by letting the patterns in the data itself reveal the appropriate models, rather than imposing a model structure that is deemed mathematically tractable from a human perspective. The fitness function that drives the evolution of the models takes into account not only error metrics (to ensure the models accurately predict the data), but also special complexity measures, thus ensuring that the resulting models reveal the data's underlying structure in a way that's understandable from a human perspective. This facilitates reasoning and favors the odds of getting insights about the data-generating system, as well as improving generalisability and extrapolation behaviour by preventing overfitting. Accuracy and simplicity may be left as two separate objectives of the regression—in which case the optimum solutions form a Pareto front—or they may be combined into a single objective by means of a model selection principle such as minimum description length. It has been proven that symbolic regression is an NP-hard problem. Nevertheless, if the sought-for equation is not too complex it is possible to solve the symbolic regression problem exactly by generating every possible function (built from some predefined set of operators) and evaluating them on the dataset in question. == Difference from classical regression == While conventional regression techniques seek to optimize the parameters for a pre-specified model structure, symbolic regression avoids imposing prior assumptions, and instead infers the model from the data. In other words, it attempts to discover both model structures and model parameters. This approach has the disadvantage of having a much larger space to search, because not only the search space in symbolic regression is infinite, but there are an infinite number of models which will perfectly fit a finite data set (provided that the model complexity isn't artificially limited). This means that it will possibly take a symbolic regression algorithm longer to find an appropriate model and parametrization, than traditional regression techniques. This can be attenuated by limiting the set of building blocks provided to the algorithm, based on existing knowledge of the system that produced the data; but in the end, using symbolic regression is a decision that has to be balanced with how much is known about the underlying system. Nevertheless, this characteristic of symbolic regression also has advantages: because the evolutionary algorithm requires diversity in order to effectively explore the search space, the result is likely to be a selection of high-scoring models (and their corresponding set of parameters). Examining this collection could provide better insight into the underlying process, and allows the user to identify an approximation that better fits their needs in terms of accuracy and simplicity. == Benchmarking == === SRBench === In 2021, SRBench was proposed as a large benchmark for symbolic regression. In its inception, SRBench featured 14 symbolic regression methods, 7 other ML methods, and 252 datasets from PMLB. The benchmark intends to be a living project: it encourages the submission of improvements, new datasets, and new methods, to keep track of the state of the art in SR. === SRBench Competition 2022 === In 2022, SRBench announced the competition Interpretable Symbolic Regression for Data Science, which was held at the GECCO conference in Boston, MA. The competition pitted nine leading symbolic regression algorithms against each other on a novel set of data problems and considered different evaluation criteria. The competition was organized in two tracks, a synthetic track and a real-world data track. ==== Synthetic Track ==== In the synthetic track, methods were compared according to five properties: re-discovery of exact expressions; feature selection; resistance to local optima; extrapolation; and sensitivity to noise. Rankings of the methods were: QLattice PySR (Python Symbolic Regression) uDSR (Deep Symbolic Optimization) ==== Real-world Track ==== In the real-world track, methods were trained to build interpretable predictive models for 14-day forecast counts of COVID-19 cases, hospitalizations, and deaths in New York State. These models were reviewed by a subject expert and assigned trust ratings and evaluated for accuracy and simplicity. The ranking of the methods was: uDSR (Deep Symbolic Optimization) QLattice geneticengine (Genetic Engine) == Non-standard methods == Most symbolic regression algorithms prevent combinatorial explosion by implementing evolutionary algorithms that iteratively improve the best-fit expression over many generations. Recently, researchers have proposed algorithms utilizing other tactics in AI. Silviu-Marian Udrescu and Max Tegmark developed the "AI Feynman" algorithm, which attempts symbolic regression by training a neural network to represent the mystery function, then runs tests against the neural network to attempt to break up the problem into smaller parts. For example, if f ( x 1 , . . . , x i , x i + 1 , . . . , x n ) = g ( x 1 , . . . , x i ) + h ( x i + 1 , . . . , x n ) {\displaystyle f(x_{1},...,x_{i},x_{i+1},...,x_{n})=g(x_{1},...,x_{i})+h(x_{i+1},...,x_{n})} , tests against the neural network can recognize the separation and proceed to solve for g {\displaystyle g} and h {\displaystyle h} separately and with different variables as inputs. This is an example of divide and conquer, which reduces the size of the problem to be more manageable. AI Feynman also transforms the inputs and outputs of the mystery function in order to produce a new function which can be solved with other techniques, and performs dimensional analysis to reduce the number of independent variables involved. The algorithm was able to "discover" 100 equations from The Feynman Lectures on Physics, while a leading software using evolutionary algorithms, Eureqa, solved only 71. AI Feynman, in contrast to classic symbolic regression methods, requires a very large dataset in order to first train the neural network and is naturally biased towards equations that are common in elementary physics.

  Read more →
• 

  POP-11

  POP-11 is a reflective, incrementally compiled programming language with many of the features of an interpreted language. It is the core language of the Poplog programming environment developed originally by the University of Sussex, and recently in the School of Computer Science at the University of Birmingham, which hosts the main Poplog website. POP-11 is an evolution of the language POP-2, developed in Edinburgh University, and features an open stack model (like Forth, among others). It is mainly procedural, but supports declarative language constructs, including a pattern matcher, and is mostly used for research and teaching in artificial intelligence, although it has features sufficient for many other classes of problems. It is often used to introduce symbolic programming techniques to programmers of more conventional languages like Pascal, who find POP syntax more familiar than that of Lisp. One of POP-11's features is that it supports first-class functions. POP-11 is the core language of the Poplog system. The availability of the compiler and compiler subroutines at run-time (a requirement for incremental compiling) gives it the ability to support a far wider range of extensions (including run-time extensions, such as adding new data-types) than would be possible using only a macro facility. This made it possible for (optional) incremental compilers to be added for Prolog, Common Lisp and Standard ML, which could be added as required to support either mixed language development or development in the second language without using any POP-11 constructs. This made it possible for Poplog to be used by teachers, researchers, and developers who were interested in only one of the languages. The most successful product developed in POP-11 was the Clementine data mining system, developed by ISL. After SPSS bought ISL, they renamed Clementine to SPSS Modeler and decided to port it to C++ and Java, and eventually succeeded with great effort, and perhaps some loss of the flexibility provided by the use of an AI language. POP-11 was for a time available only as part of an expensive commercial package (Poplog), but since about 1999 it has been freely available as part of the open-source software version of Poplog, including various added packages and teaching libraries. An online version of ELIZA using POP-11 is available at Birmingham. At the University of Sussex, David Young used POP-11 in combination with C and Fortran to develop a suite of teaching and interactive development tools for image processing and vision, and has made them available in the Popvision extension to Poplog. == Simple code examples == Here is an example of a simple POP-11 program: define Double(Source) -> Result; Source2 -> Result; enddefine; Double(123) => That prints out: 246 This one includes some list processing: define RemoveElementsMatching(Element, Source) -> Result; lvars Index; [[% for Index in Source do unless Index = Element or Index matches Element then Index; endunless; endfor; %]] -> Result; enddefine; RemoveElementsMatching("the", [[the cat sat on the mat]]) => ;;; outputs [[cat sat on mat]] RemoveElementsMatching("the", [[the cat] [sat on] the mat]) => ;;; outputs [[the cat] [sat on] mat] RemoveElementsMatching([[= cat]], [[the cat]] is a [[big cat]]) => ;;; outputs [[is a]] Examples using the POP-11 pattern matcher, which makes it relatively easy for students to learn to develop sophisticated list-processing programs without having to treat patterns as tree structures accessed by 'head' and 'tail' functions (CAR and CDR in Lisp), can be found in the online introductory tutorial. The matcher is at the heart of the SimAgent (sim_agent) toolkit. Some of the powerful features of the toolkit, such as linking pattern variables to inline code variables, would have been very difficult to implement without the incremental compiler facilities.

  Read more →
• 

  Altibase

  Altibase is a hybrid database, relational database management system manufactured by the Altibase Corporation. The software's hybrid architecture allows it to access both memory-resident and disk-resident tables using single interface. It supports both synchronous and asynchronous replication and offers real-time ACID compliance. Support is also offered for a variety of SQL standards and programming languages. Other important capabilities include data import and export, data encryption for security, multiple data access command sets, materialized view and temporary tables, and others. == History == From 1991 through 1997 the Mr. RT project was an in-memory database research project, conducted by the Electronics and Telecommunications Research Institute a government-funded research organization in South Korea. Altibase was incorporated in 1999. Altibase acquired an in-memory database engine from the Electronics and Telecommunications Research Institute in February 2000, and commercialized the database in October of the same year. In 2001, Altibase changed the name of the in-memory database product from "Spiner" to "Altibase" in 2001. In 2004, Altibase integrated the in-memory database with a disk-resident database to create a hybrid DBMS, released version 4.0 and renamed it as ALTIBASE HDB. Altibase released version 5.5.1 and 6.1.1 in 2012, version 6.3.1 in November 2013, and 6.5.1 in May 2015. Altibase claims that this is the world's first hybrid DBMS. Altibase released its open source edition version 7.1, however, closed the source in 2023. In August 2023, Altibase released its cloud-optimized version 7.3. === Awards === In 2006, Received the Presidential Award at the Korea Software Awards In 2007, Selected as World-Class Product by the Ministry of Commerce, Industry and Energy In 2009, Awarded the Outstanding Product Award in China's Telecommunications Industry In 2009, Received Outstanding Product Award at the China Billing China 2009 Telecommunication Industry Awards In 2010, Commendation from the Minister of Knowledge Economy for Technological Practicalization In 2011, Received the Grand Prize at the 10th Software Enterprise Competitiveness Award In 2011, Selected as Top 10 Emerging Technologies and received Special Award at the Korea Technology Grand Prize In 2012, Awarded for Contributions to Military Manpower Administration In 2014~2016, Included in Gartner Magic Quadrant for Operational DBMS In 2015, Selected as Outstanding BSS by China Fujian Mobile. In 2023, Awarded as the Excellent Research and Development Institution by the Korean Ministry Science and ICT In 2023, Won the Global Premium Commercial Software Presidential Award at the 9th Global Commercial Software Grand Exhibition in Korea === Release === The first version, called Spiner, was released in 2000 for commercial use. It took half of the in-memory DBMS market share in South Korea. In 2002 the second version was released renamed to Altibase v2.0. By 2003, Altibase v3.0 was released and it entered the Chinese market. Released version 4.0 with hybrid architecture, combining RAM and disk databases, was released in 2004. In 2005 Altibase began working with Chinese telecommunications providers for billing systems, and some financial companies in Taiwan, China, for home trading systems. The software was certified by the Telecommunications Technology Association. The Ministry of Government Administration and Home Affairs gave it an award in 2006. Offices in China and United States opened in 2009. In 2011, version 5.5.1 was renamed it to HDB (for "hybrid database"). The Altibase Data Stream product for complex event processing was renamed DSM. The product received a Korean technology award. Altibase introduced certification services. In 2012, HDB Zeta and Extreme were announced, and DSM renamed to CEP. In 2013, yet another variant called XDB was announced, and the company received ISO/IEC 20000 certification. In 2018, Altibase went open source. Altibase went open source in February, 2018. Altibase Corp has made the decision to discontinue the Altibase 7.1 open source edition, effective March 17, 2023. As a result, the open-source edition of Altibase 7.1 will no longer be available for download or use. Altibase released version 7.3 in September, 2023, its notable feature is the world’s first hybrid partition, allowing data to be stored in both memory and on disk at the partition level. Version 7.3 also added parallel processing capabilities for high-speed performance in both partitioned and non-partitioned scenarios. Improving potential bottlenecks associated with Commit and logging that impact transaction performance, version 7.3 has achieved an approximately 490% enhancement in performance compared to previous versions. === Release history === == Clients == According to marketing research, Altibase have over 700 customers and more than 8,000 of installations and deployments, including 22 Fortune Global 500 Companies. Altibase's clients in the telecommunications, financial services, manufacturing, and utilities sectors include Bloomberg, AT&T, LG, Intel, LGU+, ETRADE, HP, UAT Inc., POSCO, SK Telecom, KT Corporation, Samsung Electronics, Shinhan Bank, Woori Bank, Canon(Toshiba), Hanhwa, The South Korean Ministry of Defense, G-Market, CJ, and Chung-Ang University. === Global clients === Japan FX Prime, a foreign exchange services company Retela Crea Securities United States AT&T Implemented Altibase for its PS-LTE Safety network, where the Presence service plays a vital role. This service handles the reception and storage of user information, conducting real-time checks for online presence and location as needed. Canada Telus One of the major telecommunication companies. Utilizes Altibase for its operations involving real-time user management, processing high volumes of dedicated terminal data, and managing real-time location information (GIS) for terminals. Altibase contributes to the company's in-house solution for maintaining uninterrupted services during national disasters or similar situations, ensuring efficiency and reliability. China China Mobile, China Unicom, China Telecom The three major telecommunications companies. Utilize ALTIBASE HDB in 29 of 31 Chinese provinces. Turkish Ziraat Bank, Halk Bank, Deniz Bank, Garanti BBVA, TEB, Oyak Bank, QNB, Burgan Bank, and others. In 2018, Altibase entered the market through a partnership with ATP-Tradesoft, a subsidiary of Ata Holdings. Collaborating with ATP-Tradesoft. Altibase integrated into the Online Trading System XFront. This integration was well-received by major financial institutions and securities firms in Turkey. Altibase is currently implemented in the XFront Online Trading System, used by 13 significant financial institutions and banks in the Turkey. Thailand Bualuang Securities Altibase has been supplied its DBMS to support the construction of the online stock trading platform. Mongolia MobiCom The Mongolian telecommunication giant, has adopted Altibase’s 7.0 version for its mobile platform for storing the infrequently used data. Azerbaijan M1 highway Altibase has been supplied as the Database Management System (DBMS) for the electronic toll collection system. One of the most crucial transportation networks in the country. India State-owned Karur Vysya Bank In 2013, Altibase provided its hybrid database solution and was deployed for the online banking system === Industries === Telecommunications LGU+ SK Telecom KT Corporation AT&T Telus Financial services Shinhan Bank Woori Bank KakaoPay Securities Implemented Altibase in its stock trading system Leveraging Altibase's replication feature, along with offline replication through shared disk and adapter functionality, the system ensures a high level of availability and consistency, with a reliability rate of 99.999% even in the event of system failures. COREDAX Cryptocurrency market Altibase has entered into a strategic partnership by signing a database management system (DBMS) supply contract with the cryptocurrency exchange Bloomberg ETRADE Manufacturing Samsung Electronics LG POSCO Hanhwa Canon(Toshiba) Intel HP Utilities South Korean Ministry of Defense G-Market CJ UAT Inc. Chung-Ang University == Features == Altibase is a so-called "hybrid DBMS", meaning that it simultaneously supports access to both memory-resident and disk-resident tables via a single interface. It is compatible with Solaris, HP-UX, AIX, Linux, and Windows. It supports the complete SQL standard, features Multiversion concurrency control (MVCC), implements Fuzzy and Ping-Pong Checkpointing for periodically backing up memory-resident data, and ships with Replication and Database Link functionality. High performance, large -capacity service Fast real-time data processing and large amounts of data stable Provide parallel processing architecture for large data management Developed and provided Hybrid Partitioned Table function for efficiency according to data personality High stability

  Read more →
• 

  Web intelligence

  Web intelligence is the area of scientific research and development that explores the roles and makes use of artificial intelligence and information technology for new products, services and frameworks that are empowered by the World Wide Web. The term was coined in a paper written by Ning Zhong, Jiming Liu Yao and Y.Y. Ohsuga in the Computer Software and Applications Conference in 2000. == Research == The research about the web intelligence covers many fields – including data mining (in particular web mining), information retrieval, pattern recognition, predictive analytics, the semantic web, web data warehousing – typically with a focus on web personalization and adaptive websites.

  Read more →
• 

  Computational humor

  Computational humor is a branch of computational linguistics and artificial intelligence which uses computers in humor research. It is a relatively new area, with the first dedicated conference organized in 1996. The first "computer model of a sense of humor" was suggested by Suslov as early as 1992. Investigation of the general scheme of the information processing show a possibility of a specific malfunction, conditioned by the necessity of a quick deletion from consciousness of a false version. This specific malfunction can be identified with a humorous effect on the psychological grounds; however, an essentially new ingredient, a role of timing, is added to a well known role of ambiguity. In biological systems, a sense of humour inevitably develops in the course of evolution, because its biological function consists in quickening the transmission of processed information into consciousness and in a more effective use of brain resources. A realization of this algorithm in neural networks explains naturally the mechanism of laughter: deletion of a false version corresponds to zeroing of some part of the neural network and excessive energy of neurons is thrown out to the motor cortex, arousing muscular contractions. Unfortunately, a practical realization of this algorithm needs extensive databases, whose creation in the automatic regime was suggested only recently . As a result, this magistral direction was not developed properly and subsequent investigations (see below) accepted somewhat specialized colouring. == Joke generators == === Pun generation === An approach to analysis of humor is classification of jokes. A further step is an attempt to generate jokes basing on the rules that underlie classification. Simple prototypes for computer pun generation were reported in the early 1990s, based on a natural language generator program, VINCI. Graeme Ritchie and Kim Binsted in their 1994 research paper described a computer program, JAPE, designed to generate question-answer-type puns from a general, i.e., non-humorous, lexicon. (The program name is an acronym for "Joke Analysis and Production Engine".) Some examples produced by JAPE are: Q: What is the difference between leaves and a car? A: One you brush and rake, the other you rush and brake. Q: What do you call a strange market? A: A bizarre bazaar. Since then the approach has been improved, and the latest report, dated 2007, describes the STANDUP joke generator, implemented in the Java programming language. The STANDUP generator was tested on children within the framework of analyzing its usability for language skills development for children with communication disabilities, e.g., because of cerebral palsy. (The project name is an acronym for "System To Augment Non-speakers' Dialog Using Puns" and an allusion to standup comedy.) Children responded to this "language playground" with enthusiasm, and showed marked improvement on certain types of language tests. The two young people, who used the system over a ten-week period, regaled their peers, staff, family and neighbors with jokes such as: "What do you call a spicy missile? A hot shot!" Their joy and enthusiasm at entertaining others was inspirational. === Other === Stock and Strapparava described a program to generate funny acronyms. == Joke recognition == A statistical machine learning algorithm to detect whether a sentence contained a "That's what she said" double entendre was developed by Kiddon and Brun (2011). There is an open-source Python implementation of Kiddon & Brun's TWSS system. A program to recognize knock-knock jokes was reported by Taylor and Mazlack. This kind of research is important in analysis of human–computer interaction. An application of machine learning techniques for the distinguishing of joke texts from non-jokes was described by Mihalcea and Strapparava (2006). Takizawa et al. (1996) reported on a heuristic program for detecting puns in the Japanese language. == Applications == A possible application for assistance in language acquisition is described in the section "Pun generation". Another envisioned use of joke generators is in cases of a steady supply of jokes where quantity is more important than quality. Another obvious, yet remote, direction is automated joke appreciation. It is known that humans interact with computers in ways similar to interacting with other humans that may be described in terms of personality, politeness, flattery, and in-group favoritism. Therefore, the role of humor in human–computer interaction is being investigated. In particular, humor generation in user interface to ease communications with computers was suggested. Craig McDonough implemented the Mnemonic Sentence Generator, which converts passwords into humorous sentences. Based on the incongruity theory of humor, it is suggested that the resulting meaningless but funny sentences are easier to remember. For example, the password AjQA3Jtv is converted into "Arafat joined Quayle's Ant, while TARAR Jeopardized thurmond's vase," an example chosen by combining politicians names with verbs and common nouns. == Related research == John Allen Paulos is known for his interest in mathematical foundations of humor. His book Mathematics and Humor: A Study of the Logic of Humor demonstrates structures common to humor and formal sciences (mathematics, linguistics) and develops a mathematical model of jokes based on catastrophe theory. Conversational systems which have been designed to take part in Turing test competitions generally have the ability to learn humorous anecdotes and jokes. Because many people regard humor as something particular to humans, its appearance in conversation can be quite useful in convincing a human interrogator that a hidden entity, which could be a machine or a human, is in fact a human.

  Read more →
• 

  Rademacher complexity

  In computational learning theory (machine learning and theory of computation), Rademacher complexity, named after Hans Rademacher, measures richness of a class of sets with respect to a probability distribution. The concept can also be extended to real valued functions. == Definitions == === Rademacher complexity of a set === Given a set A ⊆ R m {\displaystyle A\subseteq \mathbb {R} ^{m}} , the Rademacher complexity of A is defined as follows: Rad ⁡ ( A ) := 1 m E σ [ sup a ∈ A ∑ i = 1 m σ i a i ] {\displaystyle \operatorname {Rad} (A):={\frac {1}{m}}\mathbb {E} _{\sigma }\left[\sup _{a\in A}\sum _{i=1}^{m}\sigma _{i}a_{i}\right]} where σ 1 , σ 2 , … , σ m {\displaystyle \sigma _{1},\sigma _{2},\dots ,\sigma _{m}} are independent random variables drawn from the Rademacher distribution i.e. Pr ( σ i = + 1 ) = Pr ( σ i = − 1 ) = 1 / 2 {\displaystyle \Pr(\sigma _{i}=+1)=\Pr(\sigma _{i}=-1)=1/2} for i ∈ { 1 , 2 , … , m } {\displaystyle i\in \{1,2,\dots ,m\}} , and a = ( a 1 , … , a m ) ∈ A {\displaystyle a=(a_{1},\ldots ,a_{m})\in A} . Some authors take the absolute value of the sum before taking the supremum, but if A {\displaystyle A} is symmetric this makes no difference. === Rademacher complexity of a function class === Let S = { z 1 , z 2 , … , z m } ⊆ Z {\displaystyle S=\{z_{1},z_{2},\dots ,z_{m}\}\subseteq Z} be a sample of points and consider a function class F {\displaystyle {\mathcal {F}}} of real-valued functions over Z {\displaystyle Z} . Then, the empirical Rademacher complexity of F {\displaystyle {\mathcal {F}}} given S {\displaystyle S} is defined as: Rad S ⁡ ( F ) = 1 m E σ [ sup f ∈ F | ∑ i = 1 m σ i f ( z i ) | ] {\displaystyle \operatorname {Rad} _{S}({\mathcal {F}})={\frac {1}{m}}\mathbb {E} _{\sigma }\left[\sup _{f\in {\mathcal {F}}}\left|\sum _{i=1}^{m}\sigma _{i}f(z_{i})\right|\right]} This can also be written using the previous definition: Rad S ⁡ ( F ) = Rad ⁡ ( F ∘ S ) {\displaystyle \operatorname {Rad} _{S}({\mathcal {F}})=\operatorname {Rad} ({\mathcal {F}}\circ S)} where F ∘ S {\displaystyle {\mathcal {F}}\circ S} denotes function composition, i.e.: F ∘ S := { ( f ( z 1 ) , … , f ( z m ) ) ∣ f ∈ F } {\displaystyle {\mathcal {F}}\circ S:=\{(f(z_{1}),\ldots ,f(z_{m}))\mid f\in {\mathcal {F}}\}} The worst case empirical Rademacher complexity is Rad ¯ m ( F ) = sup S = { z 1 , … , z m } Rad S ⁡ ( F ) {\displaystyle {\overline {\operatorname {Rad} }}_{m}({\mathcal {F}})=\sup _{S=\{z_{1},\dots ,z_{m}\}}\operatorname {Rad} _{S}({\mathcal {F}})} Let P {\displaystyle P} be a probability distribution over Z {\displaystyle Z} . The Rademacher complexity of the function class F {\displaystyle {\mathcal {F}}} with respect to P {\displaystyle P} for sample size m {\displaystyle m} is: Rad P , m ⁡ ( F ) := E S ∼ P m [ Rad S ⁡ ( F ) ] {\displaystyle \operatorname {Rad} _{P,m}({\mathcal {F}}):=\mathbb {E} _{S\sim P^{m}}\left[\operatorname {Rad} _{S}({\mathcal {F}})\right]} where the above expectation is taken over an identically independently distributed (i.i.d.) sample S = ( z 1 , z 2 , … , z m ) {\displaystyle S=(z_{1},z_{2},\dots ,z_{m})} generated according to P {\displaystyle P} . == Intuition == The Rademacher complexity is typically applied on a function class of models that are used for classification, with the goal of measuring their ability to classify points drawn from a probability space under arbitrary labellings. When the function class is rich enough, it contains functions that can appropriately adapt for each arrangement of labels, simulated by the random draw of σ i {\displaystyle \sigma _{i}} under the expectation, so that this quantity in the sum is maximized. The Rademacher complexity of a set A {\displaystyle A} can be rewritten as Rad ⁡ ( A ) := 1 m E σ [ sup a ∈ A ∑ i = 1 m σ i a i ] = 1 m 2 m ∑ σ ∈ { − 1 / m , + 1 / m } m [ sup a ∈ A ⟨ σ , a ⟩ ] . {\displaystyle \operatorname {Rad} (A):={\frac {1}{m}}\mathbb {E} _{\sigma }\left[\sup _{a\in A}\sum _{i=1}^{m}\sigma _{i}a_{i}\right]={\frac {1}{{\sqrt {m}}2^{m}}}\sum _{\sigma \in \{-1/{\sqrt {m}},+1/{\sqrt {m}}\}^{m}}\left[\sup _{a\in A}\langle \sigma ,a\rangle \right].} Each term in the summation is the farthest distance of the set A {\displaystyle A} from the origin, along a unit-length direction σ {\displaystyle \sigma } . The directions are along the vertices of a hypercube. Thus, we can also write it as Rad ⁡ ( A ) = 1 2 m 1 2 m − 1 ∑ σ ∈ { − 1 / m , + 1 / m } m / { − 1 , + 1 } [ sup a ∈ A ⟨ σ , a ⟩ − inf a ∈ A ⟨ σ , a ⟩ ] {\displaystyle \operatorname {Rad} (A)={\frac {1}{2{\sqrt {m}}}}{\frac {1}{2^{m-1}}}\sum _{\sigma \in \{-1/{\sqrt {m}},+1/{\sqrt {m}}\}^{m}/\{-1,+1\}}\left[\sup _{a\in A}\langle \sigma ,a\rangle -\inf _{a\in A}\langle \sigma ,a\rangle \right]} Here, the set { − 1 / m , + 1 / m } m / { − 1 , + 1 } {\displaystyle \{-1/{\sqrt {m}},+1/{\sqrt {m}}\}^{m}/\{-1,+1\}} denotes half of the vertices of a hypercube, selected so that each diagonal has exactly one vertex selected. In words, this states that 2 m Rad ⁡ ( A ) {\displaystyle 2{\sqrt {m}}\operatorname {Rad} (A)} is precisely the average width of the set A {\displaystyle A} along all diagonal directions of a hypercube. == Examples == A singleton set has 0 width in any direction, so it has Rademacher complexity 0. The set A = { ( 1 , 1 ) , ( 1 , 2 ) } ⊆ R 2 {\displaystyle A=\{(1,1),(1,2)\}\subseteq \mathbb {R} ^{2}} has average width 1 / 2 {\displaystyle 1/{\sqrt {2}}} along the two diagonal directions of the square, so it has Rademacher complexity 1 / 4 {\displaystyle 1/4} . The unit cube [ 0 , 1 ] m {\displaystyle [0,1]^{m}} has constant width m {\displaystyle {\sqrt {m}}} along the diagonal directions, so it has Rademacher complexity 1 / 2 {\displaystyle 1/2} . Similarly, the unit cross-polytope { x ∈ R m : ‖ x ‖ 1 ≤ 1 } {\displaystyle \{x\in \mathbb {R} ^{m}:\|x\|_{1}\leq 1\}} has constant width 2 / m {\displaystyle 2/{\sqrt {m}}} along the diagonal directions, so it has Rademacher complexity 1 / m {\displaystyle 1/m} . == Using the Rademacher complexity == The Rademacher complexity can be used to derive data-dependent upper-bounds on the learnability of function classes. Intuitively, a function-class with smaller Rademacher complexity is easier to learn. === Bounding the representativeness === In machine learning, it is desired to have a training set that represents the true distribution of some sample data S {\displaystyle S} . This can be quantified using the notion of representativeness. Denote by P {\displaystyle P} the probability distribution from which the samples are drawn. Denote by H {\displaystyle H} the set of hypotheses (potential classifiers) and denote by F {\displaystyle {\mathcal {F}}} the corresponding set of error functions, i.e., for every hypothesis h ∈ H {\displaystyle h\in H} , there is a function f h ∈ F {\displaystyle f_{h}\in F} , that maps each training sample (features,label) to the error of the classifier h {\displaystyle h} (note in this case hypothesis and classifier are used interchangeably). For example, in the case that h {\displaystyle h} represents a binary classifier, the error function is a 0–1 loss function, i.e. the error function f h {\displaystyle f_{h}} returns 0 if h {\displaystyle h} correctly classifies a sample and 1 else. We omit the index and write f {\displaystyle f} instead of f h {\displaystyle f_{h}} when the underlying hypothesis is irrelevant. Define: L P ( f ) := E z ∼ P [ f ( z ) ] {\displaystyle L_{P}(f):=\mathbb {E} _{z\sim P}[f(z)]} – the expected error of some error function f ∈ F {\displaystyle f\in {\mathcal {F}}} on the real distribution P {\displaystyle P} ; L S ( f ) := 1 m ∑ i = 1 m f ( z i ) {\displaystyle L_{S}(f):={1 \over m}\sum _{i=1}^{m}f(z_{i})} – the estimated error of some error function f ∈ F {\displaystyle f\in {\mathcal {F}}} on the sample S {\displaystyle S} . The representativeness of the sample S {\displaystyle S} , with respect to P {\displaystyle P} and F {\displaystyle {\mathcal {F}}} , is defined as: Rep P ⁡ ( F , S ) := sup f ∈ F ( L P ( f ) − L S ( f ) ) {\displaystyle \operatorname {Rep} _{P}({\mathcal {F}},S):=\sup _{f\in F}(L_{P}(f)-L_{S}(f))} Smaller representativeness is better, since it provides a way to avoid overfitting: it means that the true error of a classifier is not much higher than its estimated error, and so selecting a classifier that has low estimated error will ensure that the true error is also low. Note however that the concept of representativeness is relative and hence can not be compared across distinct samples. The expected representativeness of a sample can be bounded above by the Rademacher complexity of the function class: If F {\displaystyle {\mathcal {F}}} is a set of functions with range within [ 0 , 1 ] {\displaystyle [0,1]} , then Rad P , m ⁡ ( F ) − ln ⁡ 2 2 m ≤ E S ∼ P m [ Rep P ⁡ ( F , S ) ] ≤ 2 Rad P , m ⁡ ( F ) {\displaystyle \operatorname {Rad} _{P,m}({\mathcal {F}})-{\sqrt {\frac {\ln 2}{2m}}}\leq \mathbb {E} _{S\sim P^{m}}[\operatorname {Rep} _{P}({\

  Read more →
• 

  Color histogram

  In image processing and photography, a color histogram is a representation of the distribution of colors in an image. For digital images, a color histogram represents the number of pixels that have colors in each of a fixed list of color ranges that span the image's color space (the set of all possible colors). A color histogram can be built for any kind of color space, although the term is more often used for three-dimensional spaces such as RGB or HSV. For monochromatic images, the term intensity histogram may be used instead. For multi-spectral images, where each pixel is represented by an arbitrary number of measurements (for example, beyond the three measurements in RGB), a color histogram is N-dimensional, with N being the number of measurements taken. Each measurement has its own wavelength range of the light spectrum, some of which may be outside the visible spectrum. If the set of possible color values is sufficiently small, each of those colors may be placed on a range by itself; then the histogram is merely the count of pixels that have each possible color. Most often, the space is divided into an appropriate number of ranges, often arranged as a regular grid, each containing many similar color values. A color histogram may also be represented and displayed as a smooth function defined over the color space that approximates the pixel counts. Like other kinds of histograms, a color histogram is a statistic that can be viewed as an approximation of an underlying continuous distribution of color values. == Overview == Color histograms are flexible constructs that can be built from images in various color spaces, whether RGB, rg chromaticity or any other color space of any dimension. A histogram of an image is produced first by discretization of the colors in the image into a number of bins, and counting the number of image pixels in each bin. For example, a red–blue chromaticity histogram can be formed by first normalizing color pixel values by dividing RGB values by R+G+B, then quantizing the normalized R and B coordinates into N bins each. A two-dimensional histogram of red–blue chromaticity divided into four bins (N=4) may yield a histogram similar to this table: A histogram can be N-dimensional. Although harder to display, a three-dimensional color histogram for the above example could be thought of as four separate red–blue histograms, where each of the four histograms contains the red–blue values for a bin of green (0–63, 64–127, 128–191, and 192–255). The histogram provides a compact summarization of the distribution of data in an image. A color histogram of an image is relatively invariant with translation and rotation about the viewing axis, and varies only slowly with the angle of view. By comparing histogram signatures of two images and matching the color content of one image with the other, a color histogram is particularly well suited for the problem of recognizing an object of unknown position and rotation within a scene. Importantly, translation of an RGB image into the illumination invariant rg-chromaticity space allows the histogram to operate well in varying light levels. 1. What is a histogram? A histogram is a graphical representation of the number of pixels in an image. In a more simple way to explain, a histogram is a bar graph, whose X-axis represents the tonal scale (black at the left and white at the right), and Y-axis represents the number of pixels in an image in a certain area of the tonal scale. For example, the graph of a luminance histogram shows the number of pixels for each brightness level (from black to white), and when there are more pixels, the peak at the certain luminance level is higher. 2. What is a color histogram? A color histogram of an image represents the distribution of the composition of colors in the image. It shows different types of colors appeared and the number of pixels in each type of the colors appeared. The relation between a color histogram and a luminance histogram is that a color histogram can be also expressed as “three luminance histograms”, each of which shows the brightness distribution of each individual red/green/blue color channel. == Characteristics of a color histogram == A color histogram focuses only on the proportion of the number of different types of colors, regardless of the spatial location of the colors. The values of a color histogram are from statistics. They show the statistical distribution of colors and the essential tone of an image. In general, as the color distributions of the foreground and background in an image are different, there might be a bimodal distribution in the histogram. For the luminance histogram alone, there is no perfect histogram and in general, the histogram can tell whether it is over-exposure or not, but there are times when you might think the image is over exposed by viewing the histogram; however, in reality it is not. == Principles of the formation of a color histogram == The formation of a color histogram is rather simple. From the definition above, we can simply count the number of pixels for each 256 scales in each of the 3 RGB channel, and plot them on 3 individual bar graphs. In general, a color histogram is based on a certain color space, such as RGB or HSV. When we compute the pixels of different colors in an image, if the color space is large, then we can first divide the color space into certain numbers of small intervals. Each of the intervals is called a bin. This process is called color quantization. Then, by counting the number of pixels in each of the bins, we get a color histogram of the image. The concrete steps of the principles can be viewed in Example 1. == Examples == === Example 1 === Given the following image of a cat (an original version and a version that has been reduced to 256 colors for easy histogram purposes), the following data represents a color histogram in the RGB color space, using four bins. Bin 0 corresponds to intensities 0–63 Bin 1 is 64–127 Bin 2 is 128–191 and Bin 3 is 192–255. === Example 2 === Application in camera: Nowadays, some cameras have the ability to show the 3 color histograms when we take photos. We can examine clips (spikes on either the black or white side of the scale) in each of the 3 RGB color histograms. If we find one or more clipping on a channel of the 3 RGB channels, then this would result in a loss of detail for that color. To illustrate this, consider this example: We know that each of the three R, G, B channels has a range of values from 0 to 255 (8 bit). So consider a photo that has a luminance range of 0–255. Assume the photo we take is made of 4 blocks that are adjacent to each other and we set the luminance scale for each of the 4 blocks of original photo to be 10, 100, 205, 245. Thus, the image looks like the topmost figure on the right. Then, we overexpose the photo a little, say, the luminance scale of each block is increased by 10. Thus, the luminance scale for each of the 4 blocks of new photo is 20, 110, 215, 255. Then, the image looks like the second figure on the right. There is not much difference between both figures, all we can see is that the whole image becomes brighter (the contrast for each of the blocks remain the same). Now, we overexpose the original photo again, this time the luminance scale of each block is increased by 50. Thus, the luminance scale for each of the 4 blocks of the new photo is 60, 150, 255, 255. The new image now looks like the third figure on the right. Note that the scale for the last block is 255 instead of 295, for 255 is the top scale and thus the last block has clipped. When this happens, we lose the contrast of the last 2 blocks, and thus we cannot recover the image no matter how we adjust it. To conclude, when taking photos with a camera that displays histograms, always keep the brightest tone in the image below the largest scale 255 on the histogram in order to avoid losing details. == Drawbacks and other approaches == The main drawback of histograms for classification is that the representation is dependent on the color of the object being studied, ignoring its shape and texture. Color histograms can potentially be identical for two images with different object content which happens to share color information. Conversely, without spatial or shape information, similar objects of different color may be indistinguishable based solely on color histogram comparisons. There is no way to distinguish a red and white cup from a red and white plate. Put it another way: histogram-based algorithms have no concept of a generic 'cup', and a model of a red and white cup is no use when given an otherwise identical blue and white cup. Another problem is that color histograms have high sensitivity to noisy interference such as lighting intensity changes and quantization errors. High dimensionality (bins) color histograms are also another issue. Some color histogram feature spaces often occupy more than one hundred di

  Read more →
• 

  Similarity learning

  Similarity learning is an area of supervised machine learning in artificial intelligence. It is closely related to regression and classification, but the goal is to learn a similarity function that measures how similar or related two objects are. It has applications in ranking, in recommendation systems, visual identity tracking, face verification, and speaker verification. == Learning setup == There are four common setups for similarity and metric distance learning. Regression similarity learning In this setup, pairs of objects are given ( x i 1 , x i 2 ) {\displaystyle (x_{i}^{1},x_{i}^{2})} together with a measure of their similarity y i ∈ R {\displaystyle y_{i}\in R} . The goal is to learn a function that approximates f ( x i 1 , x i 2 ) ∼ y i {\displaystyle f(x_{i}^{1},x_{i}^{2})\sim y_{i}} for every new labeled triplet example ( x i 1 , x i 2 , y i ) {\displaystyle (x_{i}^{1},x_{i}^{2},y_{i})} . This is typically achieved by minimizing a regularized loss min W ∑ i l o s s ( w ; x i 1 , x i 2 , y i ) + r e g ( w ) {\displaystyle \min _{W}\sum _{i}loss(w;x_{i}^{1},x_{i}^{2},y_{i})+reg(w)} . Classification similarity learning Given are pairs of similar objects ( x i , x i + ) {\displaystyle (x_{i},x_{i}^{+})} and non similar objects ( x i , x i − ) {\displaystyle (x_{i},x_{i}^{-})} . An equivalent formulation is that every pair ( x i 1 , x i 2 ) {\displaystyle (x_{i}^{1},x_{i}^{2})} is given together with a binary label y i ∈ { 0 , 1 } {\displaystyle y_{i}\in \{0,1\}} that determines if the two objects are similar or not. The goal is again to learn a classifier that can decide if a new pair of objects is similar or not. Ranking similarity learning Given are triplets of objects ( x i , x i + , x i − ) {\displaystyle (x_{i},x_{i}^{+},x_{i}^{-})} whose relative similarity obey a predefined order: x i {\displaystyle x_{i}} is known to be more similar to x i + {\displaystyle x_{i}^{+}} than to x i − {\displaystyle x_{i}^{-}} . The goal is to learn a function f {\displaystyle f} such that for any new triplet of objects ( x , x + , x − ) {\displaystyle (x,x^{+},x^{-})} , it obeys f ( x , x + ) > f ( x , x − ) {\displaystyle f(x,x^{+})>f(x,x^{-})} (contrastive learning). This setup assumes a weaker form of supervision than in regression, because instead of providing an exact measure of similarity, one only has to provide the relative order of similarity. For this reason, ranking-based similarity learning is easier to apply in real large-scale applications. Locality sensitive hashing (LSH) Hashes input items so that similar items map to the same "buckets" in memory with high probability (the number of buckets being much smaller than the universe of possible input items). It is often applied in nearest neighbor search on large-scale high-dimensional data, e.g., image databases, document collections, time-series databases, and genome databases. A common approach for learning similarity is to model the similarity function as a bilinear form. For example, in the case of ranking similarity learning, one aims to learn a matrix W that parametrizes the similarity function f W ( x , z ) = x T W z {\displaystyle f_{W}(x,z)=x^{T}Wz} . When data is abundant, a common approach is to learn a siamese network – a deep network model with parameter sharing. == Metric learning == Similarity learning is closely related to distance metric learning. Metric learning is the task of learning a distance function over objects. A metric or distance function has to obey four axioms: non-negativity, identity of indiscernibles, symmetry and subadditivity (or the triangle inequality). In practice, metric learning algorithms ignore the condition of identity of indiscernibles and learn a pseudo-metric. When the objects x i {\displaystyle x_{i}} are vectors in R d {\displaystyle R^{d}} , then any matrix W {\displaystyle W} in the symmetric positive semi-definite cone S + d {\displaystyle S_{+}^{d}} defines a distance pseudo-metric of the space of x through the form D W ( x 1 , x 2 ) 2 = ( x 1 − x 2 ) ⊤ W ( x 1 − x 2 ) {\displaystyle D_{W}(x_{1},x_{2})^{2}=(x_{1}-x_{2})^{\top }W(x_{1}-x_{2})} . When W {\displaystyle W} is a symmetric positive definite matrix, D W {\displaystyle D_{W}} is a metric. Moreover, as any symmetric positive semi-definite matrix W ∈ S + d {\displaystyle W\in S_{+}^{d}} can be decomposed as W = L ⊤ L {\displaystyle W=L^{\top }L} where L ∈ R e × d {\displaystyle L\in R^{e\times d}} and e ≥ r a n k ( W ) {\displaystyle e\geq rank(W)} , the distance function D W {\displaystyle D_{W}} can be rewritten equivalently D W ( x 1 , x 2 ) 2 = ( x 1 − x 2 ) ⊤ L ⊤ L ( x 1 − x 2 ) = ‖ L ( x 1 − x 2 ) ‖ 2 2 {\displaystyle D_{W}(x_{1},x_{2})^{2}=(x_{1}-x_{2})^{\top }L^{\top }L(x_{1}-x_{2})=\|L(x_{1}-x_{2})\|_{2}^{2}} . The distance D W ( x 1 , x 2 ) 2 = ‖ x 1 ′ − x 2 ′ ‖ 2 2 {\displaystyle D_{W}(x_{1},x_{2})^{2}=\|x_{1}'-x_{2}'\|_{2}^{2}} corresponds to the Euclidean distance between the transformed feature vectors x 1 ′ = L x 1 {\displaystyle x_{1}'=Lx_{1}} and x 2 ′ = L x 2 {\displaystyle x_{2}'=Lx_{2}} . Many formulations for metric learning have been proposed. Some well-known approaches for metric learning include learning from relative comparisons, which is based on the triplet loss, large margin nearest neighbor, and information theoretic metric learning (ITML). In statistics, the covariance matrix of the data is sometimes used to define a distance metric called Mahalanobis distance. == Applications == Similarity learning is used in information retrieval for learning to rank, in face verification or face identification, and in recommendation systems. Also, many machine learning approaches rely on some metric. This includes unsupervised learning such as clustering, which groups together close or similar objects. It also includes supervised approaches like K-nearest neighbor algorithm which rely on labels of nearby objects to decide on the label of a new object. Metric learning has been proposed as a preprocessing step for many of these approaches. == Scalability == Metric and similarity learning scale quadratically with the dimension of the input space, as can easily see when the learned metric has a bilinear form f W ( x , z ) = x T W z {\displaystyle f_{W}(x,z)=x^{T}Wz} . Scaling to higher dimensions can be achieved by enforcing a sparseness structure over the matrix model, as done with HDSL, and with COMET. == Software == metric-learn is a free software Python library which offers efficient implementations of several supervised and weakly-supervised similarity and metric learning algorithms. The API of metric-learn is compatible with scikit-learn. OpenMetricLearning is a Python framework to train and validate the models producing high-quality embeddings. == Further information == For further information on this topic, see the surveys on metric and similarity learning by Bellet et al. and Kulis.

  Read more →
• 

  United States Tech Force

  The U.S. Tech Force (also styled as US Tech Force, Tech Force, or Government Tech Force) is a federal hiring initiative launched by the second Donald Trump administration in December 2025. The program, administered by the Office of Personnel Management (OPM), aims to recruit about 1,000 early-career technology professionals into two-year government jobs to modernize federal IT systems, advance artificial intelligence (AI) capabilities, and address technological gaps in government operations. The initiative is an effort to plug capability gaps created by Trump-administration efforts to shrink the federal government, which led to the departure of some 220,000 federal employees, including many in IT. The initiative seeks early-career workers; officials said it would offer competitive salaries and opportunities to work on high-impact government technology projects. Major technology companies—including Amazon, Apple, Microsoft, Nvidia, Meta, Google, and OpenAI—agreed to help identify and refer candidates. Candidates are allowed to take Tech Force positions on leaves of absence and without divesting their stock, raising conflict-of-interest questions. In January 2026, OPM direction Scott Kupor said the deadline for applying to Tech Force was being extended because of "tremendous interest" without saying how many people had actually applied. Also in December 2025, news broke that the administration is planning another novel use of private-sector workers: hiring cybersecurity firms for offensive cyber operations.

  Read more →
• 

  Matchbox Educable Noughts and Crosses Engine

  The Matchbox Educable Noughts and Crosses Engine (sometimes called the Machine Educable Noughts and Crosses Engine or MENACE) was a mechanical computer made from 304 matchboxes designed and built by artificial intelligence researcher Donald Michie and his colleague Roger Chambers, in 1961. It was designed to play human opponents in games of noughts and crosses (tic-tac-toe) by returning a move for any given state of play and to refine its strategy through reinforcement learning. This was one of the first types of artificial intelligence. Michie and Chambers did not have immediate access to a computer; they worked around this by building the engine out of matchboxes. The matchboxes they used each represented a single possible layout of a noughts and crosses grid. When the computer first played, it would randomly choose moves based on the current layout. As it played more games, through a reinforcement loop, it disqualified strategies that led to losing games, and supplemented strategies that led to winning games. Michie held a tournament against MENACE in 1961, wherein he experimented with different openings. Following MENACE's maiden tournament against Michie, it demonstrated successful artificial intelligence in its strategy. Michie's essays on MENACE's weight initialisation and the BOXES algorithm used by MENACE became popular in the field of computer science research. Michie was honoured for his contribution to machine learning research, and was twice commissioned to program a MENACE simulation on an actual computer. == Origin == Donald Michie (1923–2007) had been on the team decrypting the German Tunny Code during World War II. Fifteen years later, he wanted to further display his mathematical and computational prowess with an early convolutional neural network. Since computer equipment was not obtainable for such uses, and Michie did not have a computer readily available, he decided to display and demonstrate artificial intelligence in a more esoteric format and constructed a functional mechanical computer out of matchboxes and beads. MENACE was constructed as the result of a bet with a computer science colleague who postulated that such a machine was impossible. Michie undertook the task of collecting and defining each matchbox as a "fun project", later turned into a demonstration tool. Michie completed his essay on MENACE in 1963, "Experiments on the mechanization of game-learning", as well as his essay on the BOXES Algorithm, written with R. A. Chambers and had built up an AI research unit in Hope Park Square, Edinburgh, Scotland. MENACE learned by playing successive matches of noughts and crosses. Each time, it would eliminate a losing strategy by the human player confiscating the beads that corresponded to each move. It reinforced winning strategies by making the moves more likely, by supplying extra beads. This was one of the earliest versions of the Reinforcement Loop, the schematic algorithm of looping the algorithm, dropping unsuccessful strategies until only the winning ones remain. This model starts as completely random, and gradually learns. == Composition == MENACE was made from 304 matchboxes glued together in an arrangement similar to a chest of drawers. Each box had a code number, which was keyed into a chart. This chart had drawings of tic-tac-toe game grids with various configurations of X, O, and empty squares, corresponding to all possible permutations a game could go through as it progressed. After removing duplicate arrangements (ones that were simply rotations or mirror images of other configurations), MENACE used 304 permutations in its chart and thus that many matchboxes. Each individual matchbox tray contained a collection of coloured beads. Each colour represented a move on a square on the game grid, and so matchboxes with arrangements where positions on the grid were already taken would not have beads for that position. Additionally, at the front of the tray were two extra pieces of card in a "V" shape, the point of the "V" pointing at the front of the matchbox. Michie and his artificial intelligence team called MENACE's algorithm "Boxes", after the apparatus used for the machine. The first stage "Boxes" operated in five phases, each setting a definition and a precedent for the rules of the algorithm in relation to the game. == Operation == MENACE played first, as O, since all matchboxes represented permutations only relevant to the "X" player. To retrieve MENACE's choice of move, the opponent or operator located the matchbox that matched the current game state, or a rotation or mirror image of it. For example, at the start of a game, this would be the matchbox for an empty grid. The tray would be removed and lightly shaken so as to move the beads around. Then, the bead that had rolled into the point of the "V" shape at the front of the tray was the move MENACE had chosen to make. Its colour was then used as the position to play on, and, after accounting for any rotations or flips needed based on the chosen matchbox configuration's relation to the current grid, the O would be placed on that square. Then the player performed their move, the new state was located, a new move selected, and so on, until the game was finished. When the game had finished, the human player observed the game's outcome. As a game was played, each matchbox that was used for MENACE's turn had its tray returned to it ajar, and the bead used kept aside, so that MENACE's choice of moves and the game states they belonged to were recorded. Michie described his reinforcement system with "reward" and "punishment". Once the game was finished, if MENACE had won, it would then receive a "reward" for its victory. The removed beads showed the sequence of the winning moves. These were returned to their respective trays, easily identifiable since they were slightly open, as well as three bonus beads of the same colour. In this way, in future games MENACE would become more likely to repeat those winning moves, reinforcing winning strategies. If it lost, the removed beads were not returned, "punishing" MENACE, and meaning that in future it would be less likely, and eventually incapable if that colour of bead became absent, to repeat the moves that cause a loss. If the game was a draw, one additional bead was added to each box. == Results in practice == === Optimal strategy === Noughts and crosses has a well-known optimal strategy. A player must place their symbol in a way that blocks the other player from achieving any rows while simultaneously making a row themself. However, if both players use this strategy, the game always ends in a draw. If the human player is familiar with the optimal strategy, and MENACE can quickly learn it, then the games will eventually only end in draws. The likelihood of the computer winning increases quickly when the computer plays against a random-playing opponent. When playing against a player using optimal strategy, the odds of a draw grow to 100%. In Donald Michie's official tournament against MENACE in 1961 he used optimal strategy, and he and the computer began to draw consistently after twenty games. Michie's tournament had the following milestones: Michie began by consistently opening with "Variant 0", the middle square. At 15 games, MENACE abandoned all non-corner openings. At just over 20, Michie switched to consistently using "Variant 1", the bottom-right square. At 60, he returned to Variant 0. As he neared 80 games, he moved to "Variant 2", the top-middle. At 110, he switched to "Variant 3", the top right. At 135, he switched to "Variant 4", middle-right. At 190, he returned to Variant 1, and at 210, he returned to Variant 0. The trend in changes of beads in the "2" boxes runs: === Correlation === Depending on the strategy employed by the human player, MENACE produces a different trend on scatter graphs of wins. Using a random turn from the human player results in an almost-perfect positive trend. Playing the optimal strategy returns a slightly slower increase. The reinforcement does not create a perfect standard of wins; the algorithm will draw random uncertain conclusions each time. After the j-th round, the correlation of near-perfect play runs: 1 − D D − D ( j + 2 ) ∑ i = 0 j D ( j i + 1 ) V i {\displaystyle {1-D \over D-D^{(j+2)}}\sum _{i=0}^{j}D^{(ji+1)}V_{i}} Where Vi is the outcome (+1 is win, 0 is draw and -1 is loss) and D is the decay factor (average of past values of wins and losses). Below, Mn is the multiplier for the n-th round of the game. == Legacy == Donald Michie's MENACE proved that a computer could learn from failure and success to become good at a task. It used what would become core principles within the field of machine learning before they had been properly theorised. For example, the combination of how MENACE starts with equal numbers of types of beads in each matchbox, and how these are then selected at random, creates a learning behaviour similar to weight initialisation

  Read more →
• 

  STIT logic

  STIT logic (from seeing to it that) is a family of modal and branching-time logics for reasoning about agency and choice. A typical STIT operator has the form [ i s t i t : φ ] {\displaystyle [i\ {\mathsf {stit}}:\varphi ]} , usually read as "agent i {\displaystyle i} sees to it that φ {\displaystyle \varphi } ", and is interpreted in models where agents choose between alternative possible futures. STIT logics are used in action theory, deontic logic, epistemic logic, and the theory of intelligent agents to formalise notions such as "could have done otherwise", responsibility, joint action, and strategic ability in an indeterministic world. == Etymology == The acronym STIT comes from the English phrase "seeing to it that", introduced in influential work by Nuel Belnap and Michael Perloff on the logical analysis of agentive expressions. In this tradition, "to see to it that φ {\displaystyle \varphi } " is treated as a primitive agency operator, rather than being reduced to ordinary modal necessity. == History == Modern STIT logic arose in the 1980s in the context of branching-time semantics and formal theories of agency. Belnap and Perloff's article "Seeing to it that: A canonical form for agentives" introduced the idea of treating expressions of the form "agent i sees to it that φ" as a primitive modal operator, and analysed such sentences using a branching tree of moments and histories. This approach was further developed in a series of papers on indeterminism and agency and provided the conceptual core for later STIT formalisms. In the 1990s the basic formal systems of STIT logic were worked out. Horty and Belnap's influential paper on the deliberative STIT operator distinguished between a "Chellas" STIT that merely records the result of an agent's present choice and a "deliberative" STIT that requires the agent's choice to make a difference, and connected STIT with issues of action, omission, ability and obligation. Around the same time, Ming Xu proved completeness and decidability results for basic STIT systems, including a single-agent logic with Kripke-style semantics and axiomatizations for multi-agent deliberative STIT, thereby establishing STIT as a well-behaved normal modal framework. This early work was systematised in Belnap, Perloff and Xu's monograph Facing the Future: Agents and Choices in Our Indeterminist World, which presents a general branching-time semantics for individual and group STIT operators, discusses independence-of-agents conditions and articulates the metaphysical picture of an indeterministic "tree" of moments. At roughly the same time, Horty's book Agency and Deontic Logic developed deontic STIT logics in which obligations are tied to agents' available choices rather than to static states of affairs, and used the resulting systems to analyse "ought implies can", contrary-to-duty obligations and deontic paradoxes. These works helped to position STIT at the intersection of action theory, temporal logic and deontic logic. From the late 1990s and 2000s onward, STIT logics were combined with epistemic, temporal and strategic modalities. Broersen introduced complete STIT logics for knowledge and action and deontic-epistemic STIT systems that distinguish different modes of mens rea, with applications to responsibility and the specification of multi-agent systems. Work on group and coalitional agency investigated axiomatisations and complexity results for group STIT logics, and related STIT-based analyses of agency to coalition logic and alternating-time temporal logic (ATL) by exhibiting formal embeddings between the frameworks. Explicit temporal operators were added to STIT in so-called temporal STIT logics. Lorini proposed a temporal STIT with "next" and "until" operators along histories and showed how it can be applied to normative reasoning about ongoing behaviour and commitments. Ciuni and Lorini compared different semantics for temporal STIT, clarifying the relationships between branching-time, game-based and epistemic approaches, while Boudou and Lorini gave a semantics for temporal STIT based on concurrent game structures, thus strengthening links with standard models of multi-agent interaction used for ATL and strategy logic. In parallel, complexity-theoretic work by Balbiani, Herzig and Troquard and by Schwarzentruber and co-authors investigated the satisfiability and model-checking problems for various STIT fragments, showing for instance that many expressive group STIT logics are undecidable or of high computational complexity. In the 2010s, STIT ideas were combined with justification logic, imagination operators and refined deontic notions. Justification STIT logics, developed by Olkhovikov and others, merge explicit justifications with STIT-style agency so that producing a proof can itself be treated as an action that brings about knowledge, and they come with completeness and decidability results. Olkhovikov and Wansing introduced STIT imagination logics, together with axiomatic systems and tableau calculi, to model acts of voluntary imagining and their role in doxastic control. Other authors have proposed STIT-based logics of responsibility, blameworthiness and intentionality for use in philosophical and AI settings. Xu's survey article "Combinations of STIT with Ought and Know" (2015) reviews many of these developments and emphasises the interplay between deontic and epistemic STIT logics. Current research on STIT focuses on proof theory, automated reasoning and richer expressive resources. Lyon and van Berkel, building on earlier work on labelled calculi for STIT, have developed cut-free sequent systems and proof-search algorithms that yield syntactic decision procedures for a range of deontic and non-deontic multi-agent STIT logics and support applications such as duty checking and compliance checking in autonomous systems. Sawasaki has proposed first-order cstit-based STIT logics that can distinguish de re and de dicto readings of agency statements and has proved strong completeness results for Hilbert systems over finite models, moving the STIT programme beyond the purely propositional level. Further work investigates interpreted-system and computationally grounded semantics for STIT and its extensions in order to model the behaviour of autonomous agents in multi-agent settings, and proposes STIT-based semantics for epistemic notions based on patterns of information disclosure in interactive systems. == Branching-time semantics == STIT logics are usually interpreted over branching-time models. A standard STIT frame consists of: a non-empty set of moments T {\displaystyle T} , partially ordered by < {\displaystyle <} so that ( T , < ) {\displaystyle (T,<)} forms a tree (every pair of moments with a common predecessor has a greatest lower bound); a set of histories, each history being a maximal linearly ordered subset of T {\displaystyle T} ; a non-empty set of agents A g {\displaystyle Ag} ; for each agent i ∈ A g {\displaystyle i\in Ag} and moment m {\displaystyle m} , a choice function c h o i c e i m {\displaystyle {\mathsf {choice}}_{i}^{m}} that partitions the set of histories passing through m {\displaystyle m} into choice cells. The idea is that a moment represents a time at which choices are made, and histories represent complete possible future courses of events. At each moment, each agent's choice corresponds to selecting one of the available cells of histories determined by their choice function. Formulas are evaluated at pairs ( m , h ) {\displaystyle (m,h)} of a moment and a history through that moment (sometimes written m / h {\displaystyle m/h} ). A valuation assigns truth-values to atomic propositions at such indices; Boolean connectives are interpreted pointwise as in Kripke-style modal logic. == Chellas and deliberative STIT operators == Several STIT operators have been distinguished in the literature. A common approach uses two closely related operators, often called Chellas STIT and deliberative STIT. Let H m {\displaystyle H_{m}} be the set of histories passing through a moment m {\displaystyle m} , and write H m {\displaystyle H_{m}} ⟦ φ ⟧ m = { h ∈ H m ∣ M , m / h ⊨ φ } {\displaystyle {\text{⟦}}\varphi {\text{⟧}}_{m}=\{h\in H_{m}\mid M,m/h\models \varphi \}} for the set of histories at m {\displaystyle m} where φ {\displaystyle \varphi } holds. The Chellas STIT operator, often written [ i c s t i t : φ ] {\displaystyle [i\ {\mathsf {cstit}}:\varphi ]} , is given by M , m / h ⊨ [ i c s t i t : φ ] iff c h o i c e i m ( h ) ⊆ ⟦ φ ⟧ m . {\displaystyle M,m/h\models [i\ {\mathsf {cstit}}:\varphi ]\quad {\text{iff}}\quad {\mathsf {choice}}_{i}^{m}(h)\subseteq {\text{⟦}}\varphi {\text{⟧}}_{m}.} Intuitively, agent i {\displaystyle i} sees to it that φ {\displaystyle \varphi } if φ {\displaystyle \varphi } holds at all histories compatible with their present choice. The deliberative STIT operator, [ i d s t i t : φ ] {\displaystyle [i\ {\mathsf {dstit}}:\varphi ]} , adds

  Read more →
• 

  Robot learning

  Robot learning is a research field at the intersection of machine learning and robotics. It studies techniques allowing a robot to acquire novel skills or adapt to its environment through learning algorithms. The embodiment of the robot, situated in a physical embedding, provides at the same time specific difficulties (e.g. high-dimensionality, real time constraints for collecting data and learning) and opportunities for guiding the learning process (e.g. sensorimotor synergies, motor primitives). Example of skills that are targeted by learning algorithms include sensorimotor skills such as locomotion, grasping, active object categorization, as well as interactive skills such as joint manipulation of an object with a human peer, and linguistic skills such as the grounded and situated meaning of human language. Learning can happen either through autonomous self-exploration or through guidance from a human teacher, like for example in robot learning by imitation. Robot learning can be closely related to adaptive control, reinforcement learning as well as developmental robotics which considers the problem of autonomous lifelong acquisition of repertoires of skills. While machine learning is frequently used by computer vision algorithms employed in the context of robotics, these applications are usually not referred to as "robot learning". == Imitation learning == Many research groups are developing techniques where robots learn by imitating. This includes various techniques for learning from demonstration (sometimes also referred to as "programming by demonstration") and observational learning. == Sharing learned skills and knowledge == In Tellex's "Million Object Challenge", the goal is robots that learn how to spot and handle simple items and upload their data to the cloud to allow other robots to analyze and use the information. RoboBrain is a knowledge engine for robots which can be freely accessed by any device wishing to carry out a task. The database gathers new information about tasks as robots perform them, by searching the Internet, interpreting natural language text, images, and videos, object recognition as well as interaction. The project is led by Ashutosh Saxena at Stanford University. RoboEarth is a project that has been described as a "World Wide Web for robots" − it is a network and database repository where robots can share information and learn from each other and a cloud for outsourcing heavy computation tasks. The project brings together researchers from five major universities in Germany, the Netherlands and Spain and is backed by the European Union. Google Research, DeepMind, and Google X have decided to allow their robots share their experiences. == Vision-language-action model == Research groups and companies are developing vision-language-action models, foundation models that allow robotic control through the combination of vision and language. Google DeepMind, Figure AI and Hugging Face are actively working on that.

  Read more →
• 

  Machine learning in video games

  Artificial intelligence and machine learning techniques are used in video games for a wide variety of applications such as non-player character (NPC) control, procedural content generation (PCG) and deep learning-based content generation. Machine learning is a subset of artificial intelligence that uses historical data to build predictive and analytical models. This is in sharp contrast to traditional methods of artificial intelligence such as search trees and expert systems. Information on machine learning techniques in the field of games is mostly known to public through research projects as most gaming companies choose not to publish specific information about their intellectual property. The most publicly known application of machine learning in games is likely the use of deep learning agents that compete with professional human players in complex strategy games. There has been a significant application of machine learning on games such as Atari/ALE, Doom, Minecraft, StarCraft, and car racing. Other games that did not originally exists as video games, such as chess and Go have also been affected by the machine learning. == Overview of relevant machine learning techniques == === Deep learning === Deep learning is a subset of machine learning which focuses heavily on the use of artificial neural networks (ANN) that learn to solve complex tasks. Deep learning uses multiple layers of ANN and other techniques to progressively extract information from an input. Due to this complex layered approach, deep learning models often require powerful machines to train and run on. ==== Convolutional neural networks ==== Convolutional neural networks (CNN) are specialized ANNs that are often used to analyze image data. These types of networks are able to learn translation invariant patterns, which are patterns that are not dependent on location. CNNs are able to learn these patterns in a hierarchy, meaning that earlier convolutional layers will learn smaller local patterns while later layers will learn larger patterns based on the previous patterns. A CNN's ability to learn visual data has made it a commonly used tool for deep learning in games. === Recurrent neural network === Recurrent neural networks are a type of ANN that are designed to process sequences of data in order, one part at a time rather than all at once. An RNN runs over each part of a sequence, using the current part of the sequence along with memory of previous parts of the current sequence to produce an output. These types of ANN are highly effective at tasks such as speech recognition and other problems that depend heavily on temporal order. There are several types of RNNs with different internal configurations; the basic implementation suffers from a lack of long term memory due to the vanishing gradient problem, thus it is rarely used over newer implementations. ==== Long short-term memory ==== A long short-term memory (LSTM) network is a specific implementation of a RNN that is designed to deal with the vanishing gradient problem seen in simple RNNs, which would lead to them gradually "forgetting" about previous parts of an inputted sequence when calculating the output of a current part. LSTMs solve this problem with the addition of an elaborate system that uses an additional input/output to keep track of long term data. LSTMs have achieved very strong results across various fields, and were used by several monumental deep learning agents in games. === Reinforcement learning === Reinforcement learning is the process of training an agent using rewards and/or punishments. The way an agent is rewarded or punished depends heavily on the problem; such as giving an agent a positive reward for winning a game or a negative one for losing. Reinforcement learning is used heavily in the field of machine learning and can be seen in methods such as Q-learning, policy search, Deep Q-networks and others. It has seen strong performance in both the field of games and robotics. === Neuroevolution === Neuroevolution involves the use of both neural networks and evolutionary algorithms. Instead of using gradient descent like most neural networks, neuroevolution models make use of evolutionary algorithms to update neurons in the network. Researchers claim that this process is less likely to get stuck in a local minimum and is potentially faster than state of the art deep learning techniques. == Deep learning agents == Machine learning agents have been used to take the place of a human player rather than function as NPCs, which are deliberately added into video games as part of designed gameplay. Deep learning agents have achieved impressive results when used in competition with both humans and other artificial intelligence agents. === Chess === Chess is a turn-based strategy game that is considered a difficult AI problem due to the computational complexity of its board space. Similar strategy games are often solved with some form of a Minimax Tree Search. These types of AI agents have been known to beat professional human players, such as the historic 1997 Deep Blue versus Garry Kasparov match. Since then, machine learning agents have shown ever greater success than previous AI agents. === Go === Go is another turn-based strategy game which is considered an even more difficult AI problem than chess. The state space of is Go is around 10^170 possible board states compared to the 10^120 board states for Chess. Prior to recent deep learning models, AI Go agents were only able to play at the level of a human amateur. ==== AlphaGo ==== Google's 2015 AlphaGo was the first AI agent to beat a professional Go player. AlphaGo used a deep learning model to train the weights of a Monte Carlo tree search (MCTS). The deep learning model consisted of 2 ANN, a policy network to predict the probabilities of potential moves by opponents, and a value network to predict the win chance of a given state. The deep learning model allows the agent to explore potential game states more efficiently than a vanilla MCTS. The network were initially trained on games of humans players and then were further trained by games against itself. ==== AlphaGo Zero ==== AlphaGo Zero, another implementation of AlphaGo, was able to train entirely by playing against itself. It was able to quickly train up to the capabilities of the previous agent. === StarCraft series === StarCraft and its sequel StarCraft II are real-time strategy (RTS) video games that have become popular environments for AI research. Blizzard and DeepMind have worked together to release a public StarCraft 2 environment for AI research to be done on. Various deep learning methods have been tested on both games, though most agents usually have trouble outperforming the default AI with cheats enabled or skilled players of the game. ==== Alphastar ==== Alphastar was the first AI agent to beat professional StarCraft 2 players without any in-game advantages. The deep learning network of the agent initially received input from a simplified zoomed out version of the gamestate, but was later updated to play using a camera like other human players. The developers have not publicly released the code or architecture of their model, but have listed several state of the art machine learning techniques such as relational deep reinforcement learning, long short-term memory, auto-regressive policy heads, pointer networks, and centralized value baseline. Alphastar was initially trained with supervised learning, it watched replays of many human games in order to learn basic strategies. It then trained against different versions of itself and was improved through reinforcement learning. The final version was hugely successful, but only trained to play on a specific map in a protoss mirror matchup. === Dota 2 === Dota 2 is a multiplayer online battle arena (MOBA) game. Like other complex games, traditional AI agents have not been able to compete on the same level as professional human player. The only widely published information on AI agents attempted on Dota 2 is OpenAI's deep learning Five agent. ==== OpenAI Five ==== OpenAI Five utilized separate long short-term memory networks to learn each hero. It trained using a reinforcement learning technique known as Proximal Policy Learning running on a system containing 256 GPUs and 128,000 CPU cores. Five trained for months, accumulating 180 years of game experience each day, before facing off with professional players. It was eventually able to beat the 2018 Dota 2 esports champion team in a 2019 series of games. === Planetary Annihilation === Planetary Annihilation is a real-time strategy game which focuses on massive scale war. The developers use ANNs in their default AI agent. === Supreme Commander 2 === Supreme Commander 2 is a real-time strategy (RTS) video game. The game uses Multilayer Perceptrons (MLPs) to control a platoon’s reaction to encountered enemy units. Total of four MLPs are used, one for each platoon type: land, naval

  Read more →