AI Chat Bots Roleplay

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

  • VGACAD

    VGACAD

    VGACAD was the parent of a suite of shareware graphic utilities made for the MS-DOS operating system used in the IBM PC and clones. It was popular for editing and capturing images using BSAVE (graphics image format) and provided an early graphic editing suite compatible with multiple graphic cards and resolutions, used on the IBM PC. == Usage == Written by Lawrence Gozum in 1987, it was the genesis of multiple versions and improvements over 10 years. Ran with his brother, Marvin initially helped with design ideas, strategic focus, technical support calls, and managing the early shareware business. The growth of the VGACAD suite grew quickly to preoccupy most of their time. Lawrence then focused more of his efforts on software and formed Applied Insights, to manage VGACAD and its offspring, VidFun, and Ai Picture Explorer. At its peak, its users ranged from individuals, Federal government offices, museums and major newspapers. == Features == VGACAD was a misnomer, and meant VGA-Computer Assisted Drawing, rather than computer-aided design, as CAD is commonly referred to today. Its longevity was due to its color accuracy, speed, small size, and that its suite of small utilities often worked stand-alone. One called VGACAP, for 'capture', dumped video memory into a file that could later be converted to popular graphic image formats, later made commonplace when Microsoft Windows programmed the print screen key to dump graphics into the clipboard. However, VGACAP ran insulated apart from early versions of Windows, and thus could capture screens were applications prohibited such function.

    Read more →
  • Mojo (programming language)

    Mojo (programming language)

    Mojo is an in-development proprietary programming language based on Python available for Linux and macOS. Mojo aims to combine the usability of a high-level programming language, specifically Python, with the performance of a system programming language such as C++, Rust, and Zig. As of October 2025, the Mojo compiler is closed source with an open source standard library. Modular, the company behind Mojo, has stated an intent to open source the Mojo language, committing to open-source Mojo in "fall 2026". Mojo builds on the Multi-Level Intermediate Representation (MLIR) compiler software framework, instead of directly on the lower level LLVM compiler framework like many languages such as Julia, Swift, C++, and Rust. MLIR is a newer compiler framework that allows Mojo to exploit higher level compiler passes unavailable in LLVM alone, and allows Mojo to compile down and target more than only central processing units (CPUs), including producing code that can run on graphics processing units (GPUs), Tensor Processing Units (TPUs), application-specific integrated circuits (ASICs) and other accelerators. It can also often more effectively use certain types of CPU optimizations directly, like single instruction, multiple data (SIMD) with minor intervention by a developer, as occurs in many other languages. According to Jeremy Howard of fast.ai, Mojo can be seen as "syntax sugar for MLIR" and for that reason Mojo is well optimized for applications like artificial intelligence (AI). == Origin and development history == The Mojo programming language was created by Modular Inc, which was founded by Chris Lattner, the original architect of the Swift programming language and LLVM, and Tim Davis, a former Google employee. The intention behind Mojo is to bridge the gap between Python’s ease of use and the fast performance required for cutting-edge AI applications. According to public change logs, Mojo development goes back to 2022. In May 2023, the first publicly testable version was made available online via a hosted playground. By September 2023 Mojo was available for local download for Linux and by October 2023 it was also made available for download on Apple's macOS. In March 2024, Modular open sourced the Mojo standard library and started accepting community contributions under the Apache 2.0 license. == Features == Mojo was created for an easy transition from Python. The language has syntax similar to Python's, with inferred static typing, and allows users to import Python modules. It uses LLVM and MLIR as its compilation backend. The language also intends to add a foreign function interface to call C/C++ and Python code. The language is not source-compatible with Python 3, only providing a subset of its syntax, e.g. missing the global keyword, list and dictionary comprehensions, and support for classes. Further, Mojo also adds features that enable performant low-level programming: fn for creating typed, compiled functions and "struct" for memory-optimized alternatives to classes. Mojo structs support methods, fields, operator overloading, and decorators. The language also provides a borrow checker, an influence from Rust. Mojo def functions use value semantics by default (functions receive a copy of all arguments and any modifications are not visible outside the function), while Python functions use reference semantics (functions receive a reference on their arguments and any modification of a mutable argument inside the function is visible outside). The language is not currently open source, but it is planned to be made open source in the future. Modular has since committed to open-sourcing the Mojo language in "fall 2026". == Programming examples == In Mojo, functions can be declared using both fn (for performant functions) or def (for Python compatibility). Basic arithmetic operations in Mojo with a def function: and with an fn function: The manner in which Mojo employs var and let for mutable and immutable variable declarations respectively mirrors the syntax found in Swift. In Swift, var is used for mutable variables, while let is designated for constants or immutable variables. Variable declaration and usage in Mojo:

    Read more →
  • Andrej Karpathy

    Andrej Karpathy

    Andrej Karpathy (born 23 October 1986) is a Slovak-Canadian AI researcher, who co-founded and formerly worked at OpenAI, where he specialized in deep learning and computer vision. He also worked as the director of artificial intelligence and Autopilot Vision at Tesla, and in 2024 he founded Eureka Labs, an AI education platform. In 2026 he joined Anthropic as part of the pretraining team. == Education and early life == Karpathy was born in Bratislava, Czechoslovakia (now Slovakia), and moved with his family to Toronto when he was 15. He completed his Computer Science and Physics bachelor's degrees at University of Toronto in 2009 and his master's degree at University of British Columbia in 2011, where he worked on physically simulated figures (for example, a simulated runner or a simulated person in a crowd) with his adviser Michiel van de Panne. In 2006, Karpathy began posting videos on YouTube on his channel, badmephisto. He garnered fame by posting Rubik's cube tutorials which have been used by famous speedcubers such as Feliks Zemdegs. The channel has over 9 million views as of June 2025. Karpathy received a PhD from Stanford University in 2015 under the supervision of Fei-Fei Li, focusing on the intersection of natural language processing and computer vision, and deep learning models suited for this task. == Career and research == He authored and was the primary instructor of the first deep learning course at Stanford, CS 231n: Convolutional Neural Networks for Visual Recognition. The course became one of the largest classes at Stanford, growing from 150 students in 2015 to 750 in 2017. Karpathy is a founding member of the artificial intelligence research group OpenAI, where he was a research scientist from 2015 to 2017. In June 2017 he became Tesla's director of artificial intelligence and reported to Elon Musk. He was named one of MIT Technology Review's Innovators Under 35 for 2020. After taking a several-months-long sabbatical from Tesla, he announced he was leaving the company in July 2022. As of February 2023, he makes YouTube videos on how to create artificial neural networks. On February 9, 2023, Karpathy announced he was returning to OpenAI. A year later on February 13, 2024, an OpenAI spokesperson confirmed that Karpathy had left OpenAI. In the same year, he was named one of Time Magazine's 100 Most Influential People in AI. On July 16, 2024, Karpathy announced on his X account that he started a new AI education company called Eureka Labs. Their first product was the AI course, LLM101n. He also has a broader educational effort, the "Zero to Hero" series on LLM fundamentals. The company also advocates for AI teaching assistants, a concept which has been criticized due to data privacy concerns and the removal of personal connection between teacher and student. In February 2025, Karpathy coined the term vibe coding to describe how AI tools allow hobbyists to construct apps and websites just by typing prompts. On May 19, 2026, he announced that he joined Anthropic via a statement on X, while the company stated that he will be leading a team for research in pretraining.

    Read more →
  • Frame (artificial intelligence)

    Frame (artificial intelligence)

    Frames are an artificial intelligence data structure used to divide knowledge into substructures by representing "stereotyped situations". They were proposed by Marvin Minsky in his 1974 article "A Framework for Representing Knowledge". Frames are the primary data structure used in artificial intelligence frame languages; they are stored as ontologies of sets. Frames are also an extensive part of knowledge representation and reasoning schemes. They were originally derived from semantic networks and are therefore part of structure-based knowledge representations. According to Russell and Norvig's Artificial Intelligence: A Modern Approach, structural representations assemble "facts about particular object and event types and [arrange] the types into a large taxonomic hierarchy analogous to a biological taxonomy". == Frame structure == The frame contains information on how to use the frame, what to expect next, and what to do when these expectations are not met. Some information in the frame is generally unchanged while other information, stored in "terminals", usually change. Terminals can be considered as variables. Top-level frames carry information, that is always true about the problem in hand, however, terminals do not have to be true. Their value might change with the new information encountered. Different frames may share the same terminals. Each piece of information about a particular frame is held in a slot. The information can contain: Facts or Data Values (called facets) Procedures (also called procedural attachments) IF-NEEDED: deferred evaluation IF-ADDED: updates linked information Default Values For Data For Procedures Other Frames or Subframes == Features and advantages == A frame's terminals are already filled with default values, which is based on how the human mind works. For example, when a person is told "a boy kicks a ball", most people will visualize a particular ball (such as a familiar soccer ball) rather than imagining some abstract ball with no attributes. One particular strength of frame-based knowledge representations is that, unlike semantic networks, they allow for exceptions in particular instances. This gives frames a degree of flexibility that allows representations to reflect real-world phenomena more accurately. Like semantic networks, frames can be queried using spreading activation. Following the rules of inheritance, any value given to a slot that is inherited by subframes will be updated (IF-ADDED) to the corresponding slots in the subframes and any new instances of a particular frame will feature that new value as the default. Because frames are based on structures, it is possible to generate a semantic network given a set of frames even though it lacks explicit arcs. References to Noam Chomsky and his generative grammar of 1950 are generally missing from Minsky's work. The simplified structures of frames allow for easy analogical reasoning, a much prized feature in any intelligent agent. The procedural attachments provided by frames also allow a degree of flexibility that makes for a more realistic representation and gives a natural affordance for programming applications. == Example == Worth noticing here is the easy analogical reasoning (comparison) that can be done between a boy and a monkey just by having similarly named slots. Also notice that Alex, an instance of a boy, inherits default values like "Sex" from the more general parent object Boy, but the boy may also have different instance values in the form of exceptions such as the number of legs. == Frame language == A frame language is a technology used for knowledge representation in artificial intelligence. They are similar to class hierarchies in object-oriented languages although their fundamental design goals are different. Frames are focused on explicit and intuitive representation of knowledge whereas objects focus on encapsulation and information hiding. Frames originated in AI research and objects primarily in software engineering. However, in practice, the techniques and capabilities of frame and object-oriented languages overlap significantly. === Example === A simple example of concepts modeled in a frame language is the Friend of A Friend (FOAF) ontology defined as part of the Semantic Web as a foundation for social networking and calendar systems. The primary frame in this simple example is a Person. Example slots are the person's email, home page, phone, etc. The interests of each person can be represented by additional frames describing the space of business and entertainment domains. The slot knows links each person with other persons. Default values for a person's interests can be inferred by the web of people they are friends of. === Implementations === The earliest frame-based languages were custom developed for specific research projects and were not packaged as tools to be re-used by other researchers. Just as with expert system inference engines, researchers soon realized the benefits of extracting part of the core infrastructure and developing general-purpose frame languages that were not coupled to specific applications. One of the first general-purpose frame languages was KRL. One of the most influential early frame languages was KL-ONE. KL-ONE spawned several subsequent Frame languages. One of the most widely used successors to KL-ONE was the Loom language developed by Robert MacGregor at the Information Sciences Institute. In the 1980s, Artificial Intelligence generated a great deal of interest in the business world fueled by expert systems. This led to the development of many commercial products for the development of knowledge-based systems. These early products were usually developed in Lisp and integrated constructs such as IF-THEN rules for logical reasoning with Frame hierarchies for representing data. One of the most well known of these early Lisp knowledge-base tools was the Knowledge Engineering Environment (KEE) from Intellicorp. KEE provided a full Frame language with multiple inheritance, slots, triggers, default values, and a rule engine that supported backward and forward chaining. As with most early commercial versions of AI software KEE was originally deployed in Lisp on Lisp machine platforms but was eventually ported to PCs and Unix workstations. The research agenda of the Semantic Web spawned a renewed interest in automatic classification and frame languages. An example is the Web Ontology Language (OWL) standard for describing information on the Internet. OWL is a standard to provide a semantic layer on top of the Internet. The goal is that rather than searching the web using keywords as most search engines (e.g. Google) do today, the web can be organized by concepts organized in an ontology, like a directory structure. The name of the OWL language itself provides a good example of the value of a Semantic Web. If one were to search for "OWL" using the Internet today most of the pages retrieved would be on the bird Owl rather than the standard OWL. With a Semantic Web it would be possible to specify the concept "Web Ontology Language" and the user would not need to worry about the various possible acronyms or synonyms as part of the search. Likewise, the user would not need to worry about homonyms crowding the search results with irrelevant data such as information about birds of prey as in this simple example. In addition to OWL, various standards and technologies that are relevant to the Semantic Web and were influenced by Frame languages include OIL and DAML. The Protege Open Source software tool from Stanford University provides an ontology editing capability that is built on OWL and has the full capabilities of a classifier. However it ceased to explicitly support frames as of version 3.5 (which is maintained for those preferring frame orientation), with the current version being 5.6.8 as of 2025. The justification for moving from explicit frames being that OWL DL is more expressive and "industry standard". === Comparison of frames and objects === Frame languages have a significant overlap with object-oriented languages. The terminologies and goals of the two communities were different but as they moved from the academic world and labs to the commercial world developers tended to not care about philosophical issues and focused primarily on specific capabilities, taking the best from either camp regardless of where the idea began. What both paradigms have in common is a desire to reduce the distance between concepts in the real world and their implementation in software. As such both paradigms arrived at the idea of representing the primary software objects in taxonomies starting with very general types and progressing to more specific types. The following table illustrates the correlation between standard terminology from the object-oriented and frame language communities: The primary difference between the two paradigms was in the degree that encapsulation was considered a majo

    Read more →
  • Kernel-phase

    Kernel-phase

    Kernel-phases are observable quantities used in high resolution astronomical imaging used for superresolution image creation. It can be seen as a generalization of closure phases for redundant arrays. For this reason, when the wavefront quality requirement are met, it is an alternative to aperture masking interferometry that can be executed without a mask while retaining phase error rejection properties. The observables are computed through linear algebra from the Fourier transform of direct images. They can then be used for statistical testing, model fitting, or image reconstruction. == Prerequisites == In order to extract kernel-phases from an image, some requirements must be met: Images are nyquist-sampled (at least 2 pixels per resolution element ( λ D {\displaystyle {\frac {\lambda }{D}}} )) Images are taken in near monochromatic light Exposure time is shorter than the timescale of aberrations Strehl ratio is high (good adaptive optics) Linearity of the pixel response (i.e. no saturation) Deviations from these requirements are known to be acceptable, but lead to observational bias that should be corrected by the observation of calibrators. == Definition == The method relies on a discrete model of the instrument's pupil plane and the corresponding list of baselines to provide corresponding vectors φ {\displaystyle \varphi } of pupil plane errors and Φ {\displaystyle \Phi } of image plane Fourier Phases. When the wavefront error in the pupil plane is small enough (i.e. when the Strehl ratio of the imaging system is sufficiently high), the complex amplitude associated to the instrumental phase in one point of the pupil φ k {\displaystyle \varphi _{k}} , can be approximated by e i φ k ≈ 1 + i φ k {\displaystyle e^{i\varphi _{k}}\approx 1+{\mathit {i}}\varphi _{k}} . This permits the expression of the pupil-plane phase aberrations φ {\displaystyle \varphi } to the image plane Fourier phase as a linear transformation described by the matrix A {\displaystyle A} : Φ = Φ 0 + A ⋅ φ {\displaystyle \Phi =\Phi _{0}+A\cdot \varphi } Where Φ 0 {\displaystyle \Phi _{0}} is the theoretical Fourier phase vector of the object. In this formalism, singular value decomposition can be used to find a matrix K {\displaystyle K} satisfying K ⋅ A = 0 {\displaystyle K\cdot A=0} . The rows of K {\displaystyle K} constitute a basis of the kernel of A T {\displaystyle A^{T}} . K ⋅ Φ = K ⋅ Φ 0 + K ⋅ A ⋅ φ {\displaystyle K\cdot \Phi =K\cdot \Phi _{0}+{\cancel {K\cdot A\cdot \varphi }}} The vector K . Φ {\displaystyle K.\Phi } is called the kernel-phase vector of observables. This equation can be used for model-fitting as it represents the interpretation of a sub-space of the Fourier phase that is immune to the instrumental phase errors to the first order. == Applications == The technique was first used in the re-analysis of archival images from the Hubble Space Telescope where it enabled the discovery of a number of brown dwarf in close binary systems. The technique is used as an alternative to aperture masking interferometry, especially for fainter stars because it does not require the use of masks that typically block 90% of the light, and therefore allows higher throughput. It is also considered to be an alternative to coronagraphy for direct detection of exoplanets at very small separations (below 2 λ D {\displaystyle 2{\frac {\lambda }{D}}} ) where coronagraphs are limited by the wavefront errors of adaptive optics. The same framework can be used for wavefront sensing. In the case of an asymmetric aperture, a pseudo-inverse of A {\displaystyle A} can be used to reconstruct the wavefront errors directly from the image. A Python library called xara is available on GitHub and maintained by Frantz Martinache to facilitate the extraction and interpretation of kernel-phases. The KERNEL project, has received funding from the European Research Council to explore the potential of these observables for a number of use-cases, including direct detection of exoplanets, image reconstruction, and image plane wavefront sensing for adaptive optics.

    Read more →
  • Xinhua–Sogou AI news anchor

    Xinhua–Sogou AI news anchor

    Xinhua News Agency and Sogou of China developed an artificial intelligence (AI) for news reporting purposes. The AI was unveiled in 2018. It is touted to be the "world's first AI news anchor". == History == The AI was unveiled at the 2018 World Internet Conference in Wuzhen, Zhejiang, China. The AI devises avatars patterned after real life Xinhua anchors. The AI patterned after Qiu Hao spoke in Chinese, while the one derived from the likeness of Zhang Zhao speaks in English. The unveiling of the AI raised concerns of its impact on employment. Xinhua and Sogou unveiled Xin Xiaomeng, an AI with a female avatar in 2019. People's Daily followed suit by unveiling its own AI newscaster in 2023.

    Read more →
  • Framework Convention on Artificial Intelligence

    Framework Convention on Artificial Intelligence

    The Framework Convention on Artificial Intelligence and Human Rights, Democracy and the Rule of Law (also called Framework Convention on Artificial Intelligence or AI convention) is an international treaty on artificial intelligence. It was adopted under the auspices of the Council of Europe (CoE) and signed on 5 September 2024. The treaty aims to ensure that the development and use of AI technologies align with fundamental human rights, democratic values, and the rule of law, addressing risks such as misinformation, algorithmic discrimination, and threats to public institutions. More than 50 countries, including the EU member states, have endorsed the Framework Convention on Artificial Intelligence. == Background == The development of the Framework Convention on AI emerged in response to growing concerns over the ethical, legal, and societal impacts of artificial intelligence. The Council of Europe, which has historically played a key role in setting human rights standards across Europe, initiated discussions on AI governance in 2020, leading to the drafting of a binding legal framework. The process of creating the Framework Convention began in 2019 with the ad hoc Committee on Artificial Intelligence (CAHAI) assessing the feasibility of the instrument. In 2022, the Committee on Artificial Intelligence (CAI) took over the process, drafting and negotiating the text of the Convention. The treaty is designed to complement existing international human rights instruments, including the European Convention on Human Rights and the Convention for the Protection of Individuals with regard to Automatic Processing of Personal Data. == Structure and content == The Convention establishes fundamental principles for AI governance, including transparency, accountability, non-discrimination, and human rights protection through eight chapters and 26 articles. Adopted in 2024, this landmark treaty addresses AI governance through seven core principles and detailed implementation mechanisms. It mandates risk and impact assessments to mitigate potential harms and provides safeguards such as the right to challenge AI-driven decisions. It applies to public authorities and private entities acting on their behalf but excludes national security and defense activities. Implementation is overseen by a Conference of the Parties, ensuring compliance and international cooperation. Activities within the AI system lifecycle must adhere to seven fundamental principles, ensuring compliance with human rights, democracy, and the rule of law. The treaty also establishes remedies, procedural rights and safeguards, and risk and impact management requirements to promote accountability, transparency, and responsible AI development. The treaty consists of five chapters. Chapter I contains general provisions. Chapter II states the general obligation to protect human rights and the integrity of democratic processes and respect of the rule of law. The main principles and rights are contained in Chapter III, which consists of Articles 6 to 13. Chapter IV (Articles 14 to 15) sets up the legal remedies. Chapter V states the risk and impact management framework. Chapter VI facilitates the implementation criteria of the treaty. Chapter VII sets the co-operation and oversight mechanisms. Chapter VIII contains various concluding clauses. Article 1 declares the objectives of the treaty, to ensure that activities within the lifecycle of artificial intelligence systems are fully consistent with human rights, democracy and the rule of law. == Entry into force == The treaty will enter into force on the first day of the month following the expiration of a period of three months after the date on which five ratification made by five countries, including three member states of the Council of Europe. == Competing approaches == While the CoE's AI Convention represents a multilateral effort to regulate AI through a human rights-based approach, alternative frameworks have also been proposed. One notable example is the Munich Draft for a Convention on AI, Data and Human Rights, an initiative led by legal scholars and policymakers in Germany. The Munich Draft advocates for stronger safeguards against AI-related risks, emphasizing stricter data protection measures, accountability for AI developers, and explicit prohibitions on high-risk AI applications, such as mass surveillance and autonomous lethal weapons. Unlike the CoE convention, which focuses on balancing innovation with regulation, the Munich Draft takes a more precautionary stance, calling for tighter controls over AI deployment in sensitive domains. Other competing international efforts include the OECD’s AI Principles, the GPAI (Global Partnership on AI), and the European Union's AI Act, each of which offers different regulatory strategies to govern AI at regional and global levels. == Signatories == Signatories include Andorra, Canada, the European Union, Georgia, Iceland, Israel, Japan, Liechtenstein, the Republic of Moldova, Montenegro, Norway, San Marino, Switzerland, Ukraine, the United Kingdom, the United States, and Uruguay. == Endorsement == The treaty was widely endorsed by leading AI policy experts, including Stuart J. Russell, Virginia Dignum, Emma Ruttkamp-Bloem, Pascal Pichonnaz, Maria Helen Murphy, Angella Ndaka, Hannes Werthner, Katja Langenbucher, Gry Hasselbalch, Ricardo Baeza-Yates, Kutoma Wakunuma, Gianclaudio Malgieri, Oreste Pollicino, Nagla Rizk, Giovanni Sartor, Lee Tiedrich, Ingrid Schneider, Eduardo Bertoni, Garry Kasparov, Merve Hikcok, and Marc Rotenberg. The treaty was also endorsed by notable political leaders, including Theodoros Roussopoulos, President of the Parliamentart Assembly in the Council of Europe, and Christopher Holmes, Member of the House of Lords of the United Kingdom, and by the International Bar Association (IBA), and personally by Almudena Arpón de Mendívil, President of the IBA. The Center for AI and Digital Policy (CAIDP) has been carrying out a campaign to promote endorsement of the treaty by urging various countries to sign and ratify the treaty. The CAIDP further urged the countries to make a clear and firm commitment to ensure the full inclusion of the private sector under the treaty’s provisions.

    Read more →
  • MuZero

    MuZero

    MuZero is a computer program developed by artificial intelligence research company DeepMind, a subsidiary of Google, to master games without knowing their rules and underlying dynamics. Its release in 2019 included benchmarks of its performance in Go, chess, shogi, and a suite of 57 different Atari games. The algorithm uses an approach similar to AlphaZero, where a combination of a tree-based search and a learned model is deployed. It matched AlphaZero's performance in chess and shogi, improved on its performance in Go, and improved on the state of the art in mastering a suite of 57 Atari games (the Arcade Learning Environment), a visually-complex domain. MuZero was trained via self-play, with no access to rules, opening books, or endgame tablebases. The trained algorithm used the same convolutional and residual architecture as AlphaZero, but with 20 percent fewer computation steps per node in the search tree. == History == MuZero really is discovering for itself how to build a model and understand it just from first principles. On November 19, 2019, the DeepMind team released a preprint introducing MuZero. === Derivation from AlphaZero === MuZero (MZ) is a combination of the high-performance planning of the AlphaZero (AZ) algorithm with approaches to model-free reinforcement learning. The combination allows for more efficient training in classical planning regimes, such as Go, while also handling domains with much more complex inputs at each stage, such as visual video games. MuZero was derived directly from AZ code, sharing its rules for setting hyperparameters. Differences between the approaches include: AZ's planning process uses a simulator. The simulator knows the rules of the game. It has to be explicitly programmed. A neural network then predicts the policy and value of a future position. Perfect knowledge of game rules is used in modeling state transitions in the search tree, actions available at each node, and termination of a branch of the tree. MZ does not have access to the rules, and instead learns one with neural networks. AZ has a single model for the game (from board state to predictions); MZ has separate models for representation of the current state (from board state into its internal embedding), dynamics of states (how actions change representations of board states), and prediction of policy and value of a future position (given a state's representation). MZ's hidden model may be complex, and it may turn out it can host computation; exploring the details of the hidden model in a trained instance of MZ is a topic for future exploration. MZ does not expect a two-player game where winners take all. It works with standard reinforcement-learning scenarios, including single-agent environments with continuous intermediate rewards, possibly of arbitrary magnitude and with time discounting. AZ was designed for two-player games that could be won, drawn, or lost. === Comparison with R2D2 === The previous state of the art technique for learning to play the suite of Atari games was R2D2, the Recurrent Replay Distributed DQN. MuZero surpassed both R2D2's mean and median performance across the suite of games, though it did not do better in every game. == Training and results == MuZero used 16 third-generation tensor processing units (TPUs) for training, and 1000 TPUs for selfplay for board games, with 800 simulations per step and 8 TPUs for training and 32 TPUs for selfplay for Atari games, with 50 simulations per step. AlphaZero used 64 second-generation TPUs for training, and 5000 first-generation TPUs for selfplay. As TPU design has improved (third-generation chips are 2x as powerful individually as second-generation chips, with further advances in bandwidth and networking across chips in a pod), these are comparable training setups. R2D2 was trained for 5 days through 2M training steps. === Initial results === MuZero matched AlphaZero's performance in chess and shogi after roughly 1 million training steps. It matched AZ's performance in Go after 500,000 training steps and surpassed it by 1 million steps. It matched R2D2's mean and median performance across the Atari game suite after 500 thousand training steps and surpassed it by 1 million steps, though it never performed well on 6 games in the suite. == Reactions and related work == MuZero was viewed as a significant advancement over AlphaZero, and a generalizable step forward in unsupervised learning techniques. The work was seen as advancing understanding of how to compose systems from smaller components, a systems-level development more than a pure machine-learning development. While only pseudocode was released by the development team, Werner Duvaud produced an open source implementation based on that. MuZero has been used as a reference implementation in other work, for instance as a way to generate model-based behavior. In late 2021, a more efficient variant of MuZero was proposed, named EfficientZero. It "achieves 194.3 percent mean human performance and 109.0 percent median performance on the Atari 100k benchmark with only two hours of real-time game experience". In early 2022, a variant of MuZero was proposed to play stochastic games (for example 2048, backgammon), called Stochastic MuZero, which uses afterstate dynamics and chance codes to account for the stochastic nature of the environment when training the dynamics network.

    Read more →
  • IQTELL

    IQTELL

    IQTELL was a productivity app that allowed users to manage email, tasks, projects, calendars, contacts, Evernotes and more in a single app. IQTELL was available as a web app, as well as an iOS and Android app. All user information was automatically synced between all devices. iOS and Android apps supported offline access. The app could be used to implement concepts and techniques described in the book Getting Things Done by David Allen. == History == IQTELL was created by Ran Flam and released in 2013. In 2014, mobile apps for iOS and Android were released. In 2015, Premium and Platinum subscription plans were introduced (while maintaining the free user version). In April 2017, a new web app was launched. On July 31, 2017, all IQTell services have been closed. == Productivity methods == IQTell was designed to fit in with the Getting Things Done (GTD) productivity methods. Users may have had utilized GTD lists, such as Inbox, Actions, Projects, Someday, Ticklers, and Reference information to process their Inbox items into relevant GTD lists. Using the web app, iOS and/or Android apps, users could deploy macros/shortcuts to quickly process their email. Email was turned into tasks (actions), projects, etc. The original email was removed from the email inbox. The email became a part of the items created (e.g. actions, project, etc.) and could also be viewed in the All Mail folder (if Gmail), or the Archive folder (if non-Gmail). Users had flexibility to use the out-of-the-box macros/shortcuts as well as edit/create additional macros. IQTELL features included email, calendars, contacts, list management, sharing and collaboration with team members. All of the features were compatible with commonly used organization software such as Evernote and iCloud.

    Read more →
  • Mycin

    Mycin

    MYCIN was an early backward chaining expert system that used black box to identify bacteria causing severe infections, such as bacteremia and meningitis, and to recommend antibiotics, with the dosage adjusted for patient's body weight — the name derived from the antibiotics themselves, as many antibiotics have the suffix "-mycin". The Mycin system was also used for the diagnosis of blood clotting diseases. MYCIN was developed over five or six years in the early 1970s at Stanford University. It was written in Lisp as the doctoral dissertation of Edward Shortliffe under the direction of Bruce G. Buchanan, Stanley N. Cohen and others. MYCIN emerged from the Stanford Heuristic Programming Project. MYCIN demonstrated the potential for expert systems in building high-performance medical reasoning programs. MYCIN is often viewed as a pioneer in the field of expert systems, even being referred to as the "grandaddy of them all-the one that launched the field" by Dr. Allen Newell. MYCIN led to the EMYCIN expert system shell ("essential MYCIN") for acquiring knowledge, reasoning with it, and explaining the results, without the specific medical knowledge. It can be described as "EMYCIN = Prolog + uncertainty + caching + questions + explanations + contexts - variables". An introduction is in Chapter 16 of Paradigms of Artificial Intelligence Programming (PAIP). == Method == MYCIN operated using a fairly simple inference engine and a knowledge base of ~600 rules by obtaining individual inferential facts identified by experts and encoding such facts as individual production rules. No other AI program at the time contained as much domain-specific knowledge clearly separated from its inference procedures as MYCIN. It would query the physician running the program via a long series of simple yes/no or textual questions. At the end, it provided a list of possible culprit bacteria ranked from high to low based on the probability of each diagnosis, its confidence in each diagnosis' probability, the reasoning behind each diagnosis (that is, MYCIN would also list the questions and rules which led it to rank a diagnosis a particular way), and its recommended course of drug treatment. MYCIN could additionally respond to queries by physicians related to why it asked the user a certain question, how it arrived at a conclusion, and why it did not consider certain factors. The developers performed studies showing that MYCIN's performance was minimally affected by perturbations in the uncertainty metrics associated with individual rules, suggesting that the power in the system was related more to its knowledge representation and reasoning scheme than to the details of its numerical uncertainty model. Some observers felt that it should have been possible to use classical Bayesian statistics. MYCIN's developers argued that this would require either unrealistic assumptions of probabilistic independence, or require the experts to provide estimates for an unfeasibly large number of conditional probabilities. Subsequent studies later showed that the certainty factor model could indeed be interpreted in a probabilistic sense, and highlighted problems with the implied assumptions of such a model. However the modular structure of the system would prove very successful, leading to the development of graphical models such as Bayesian networks. === Context === A context in MYCIN determines what types of objects can be reasoned about. They are similar to variables in Prolog, or environment variables in operating systems. === Evidence combination === In MYCIN it was possible that two or more rules might draw conclusions about a parameter with different weights of evidence. For example, one rule may conclude that the organism in question is E. Coli with a certainty of 0.8 whilst another concludes that it is E. Coli with a certainty of 0.5 or even −0.8. In the event the certainty is less than zero the evidence is actually against the hypothesis. In order to calculate the certainty factor MYCIN combined these weights using the formula below to yield a single certainty factor: C F ( x , y ) = { X + Y − X Y if X , Y > 0 X + Y + X Y if X , Y < 0 X + Y 1 − min ( | X | , | Y | ) otherwise {\displaystyle CF(x,y)={\begin{cases}X+Y-XY&{\text{if }}X,Y>0\\X+Y+XY&{\text{if }}X,Y<0\\{\frac {X+Y}{1-\min(|X|,|Y|)}}&{\text{otherwise}}\end{cases}}} Where X and Y are the certainty factors. This formula can be applied more than once if more than two rules draw conclusions about the same parameter. It is commutative, so it does not matter in which order the weights were combined. The combination formula was designed to have the following desirable properties: −1 can be interpreted as "false", +1 as "true", and 0 as "uncertain". Combining unknown with anything leaves it unchanged. Combining true with anything (except false) gives true. Similarly for false. Combining true and false is a division-by-zero error. Combining +x and -x gives unknown. Combining two positives (except true) gives a larger positive. Similarly for negatives. Combining a positive and a negative gives something in between. === Examples === The following examples come from Chapter 16 of PAIP, which contains an implementation in Common Lisp of a modified and simplified version of MYCIN for pedagogical purposes. A rule, and an English paraphrase generated by the system: == Results == An evaluation of MYCIN was conducted at the Stanford Medical School. The first phase of the evaluation consisted of 10 test cases of diverse origin, chosen by a physician who was not acquainted with MYCIN's methods or knowledge base. These cases were presented to 7 physicians and 1 senior medical student. 10 prescriptions were compiled for each of the cases, 1 recommended by MYCIN, 1 prescribed by the treating physician at the county hospital, and 8 by the aforementioned individuals. The second phase of the evaluation consisted of eight infectious disease specialists being provided the clinical summary and set of 10 prescriptions for each of the 10 cases and tasked to provide their own recommendations for each case and assess the 10 prescriptions. MYCIN received an acceptability rating of 65%, which was comparable to the 42.5% to 62.5% rating of five faculty members. This study is often cited as showing the potential for disagreement about therapeutic decisions, even among experts, when there is no "gold standard" for correct treatment. == Practical use == MYCIN was never actually used in practice. This wasn't because of any weakness in its performance. Some observers raised ethical and legal issues related to the use of computers in medicine, regarding the responsibility of the physicians in case the system gave wrong diagnosis. However, the greatest problem, and the reason that MYCIN was not used in routine practice, was the state of technologies for system integration, especially at the time it was developed. MYCIN was a stand-alone system that required a user to enter all relevant information about a patient by typing in responses to questions MYCIN posed. MYCIN ran on the DEC KI10 PDP-10, supporting a large time-shared system available over the early Internet (ARPANet), before personal computers were developed. MYCIN's greatest influence was accordingly its demonstration of the power of its representation and reasoning approach. Rule-based systems in many non-medical domains were developed in the years that followed MYCIN's introduction of the approach. In the 1980s, expert system "shells" were introduced (including one based on MYCIN, known as E-MYCIN (followed by Knowledge Engineering Environment - KEE)) and supported the development of expert systems in a wide variety of application areas. A difficulty that rose to prominence during the development of MYCIN and subsequent complex expert systems has been the extraction of the necessary knowledge for the inference engine to use from the human expert in the relevant fields into the rule base (the so-called "knowledge acquisition bottleneck").

    Read more →
  • Vilém Flusser

    Vilém Flusser

    Vilém Flusser (May 12, 1920 – November 27, 1991) was a Czech-born Brazilian philosopher, writer and journalist, best known for his contributions to media studies, communication theory, and the philosophy of language. He lived for a long period in São Paulo (where he became a Brazilian citizen) and later in France, and his works are written in many different languages. His early work was marked by discussion of the thought of Martin Heidegger, and by the influence of existentialism and phenomenology. Phenomenology would play a major role in the transition to the later phase of his work, in which he turned his attention to the philosophy of communication and of artistic production. He contributed to the dichotomy logic theory through history: the period of image worship, and period of text worship, with deviations consequently into idolatry and "textolatry". == Life == Flusser was born in 1920 in Prague, Czechoslovakia into a family of Jewish intellectuals. His father, Gustav Flusser, studied mathematics and physics (under Albert Einstein among others). Vilém attended German and Czech primary schools and later a German grammar school. In 1938, Flusser started to study philosophy at the Juridical Faculty of the Charles University in Prague. In 1939, shortly after the Nazi occupation, Flusser emigrated to London (with Edith Barth, his later wife, and her parents) to continue his studies for one term at the London School of Economics and Political Science. Vilém Flusser lost all of his family in the German concentration camps: his father died in Buchenwald in 1940; his grandparents, his mother and his sister were brought to Theresienstadt and later to Auschwitz where they were killed. The next year, he emigrated to Brazil, living both in São Paulo and Rio de Janeiro. He started working at a Czech import/export company and then at Stabivolt, a manufacturer of radios and transistors. In 1960 he started to collaborate with the Brazilian Institute of Philosophy (IBF) in São Paulo and published in the Revista Brasileira de Filosofia; by these means he seriously approached the Brazilian intellectual community. Flusser had as his friend and closest interlocutor the Brazilian philosopher Vicente Ferreira da Silva. Flusser and Vicente Ferreira da Silva met in São Paulo in the 1960s and began a close intellectual dialogue that continued until Ferreira da Silva's death in 1963. Flusser wrote several essays on Ferreira da Silva's work and that Ferreira da Silva's concept of "Fundamental ontology” had a significant impact on Flusser's understanding of the nature of reality. During the 60s Flusser published and taught at several schools in São Paulo, being Lecturer for Philosophy of Science at the Escola Politécnica of the University of São Paulo and Professor of Philosophy of Communication at the Escola Dramática and the Escola Superior de Cinema in São Paulo. He also participated actively in the arts, collaborating with the Bienal de São Paulo, among other cultural events. Beginning in the 1950s he taught philosophy and worked as a journalist, before publishing his first book Língua e realidade (Language and Reality) in 1963. In 1972 he decided to leave Brazil. Some say it was because it was becoming difficult to publish because of the military regime. Others dispute this reason, since his work on communication and language did not threaten the military. In 1970, when a reform took place at the University of São Paulo by the Brazilian military government, all Lecturers of Philosophy (members of the Department of Philosophy) were dismissed. Flusser, who taught at the Engineering School (Escola Politécnica), had to leave the university as well. In 1972 he and his wife Edith settled temporarily in Merano (Tyrol). Further short stays in various European countries followed until they moved to Robion in southern France in 1981, where they remained until Flusser's death in 1991. To the end of his life, he was quite active writing and giving lectures around media theory and working with new topics (Philosophy of Photography, Technical Images, etc.). He died in 1991 in a car accident near the Czech–German border, while trying to visit his native city, Prague, to give a lecture. Vilém Flusser is the cousin of David Flusser. == Philosophy == Flusser's essays are short, provocative and lucid, with a resemblance to the style of journalistic articles. Critics have noted he is less a 'systematic' thinker than a 'dialogic' one, purposefully eclectic and provocative (Cubitt 2004). However, his early books, written in the 1960s, primarily in Portuguese, and published in Brazil, have a slightly different style. Flusser's writings relate to each other, however, which means that he intensively works over certain topics and dissects them into a number of brief essays. His main topics of interest were: epistemology, ethics, aesthetics, ontology, language philosophy, semiotics, philosophy of science, the history of Western culture, the philosophy of religion, the history of symbolic language, technology, writing, the technical image, photography, migration, media and literature, and, especially in his later years, the philosophy of communication and of artistic production. His writings reflect his wandering life: although the majority of his work was written in German and Portuguese, he also wrote in English and French, with scarce translation to other languages. Because Flusser's writings in different languages are dispersed in the form of books, articles or sections of books, his work as a media philosopher and cultural theorist is only now becoming more widely known. The first book by Flusser to be published in English was Towards a Philosophy of Photography in 1984 by the then new journal European Photography, which was his own translation of the work. The Shape of Things, was published in London in 1999 and was followed by a new translation of Towards a Philosophy of Photography. Flusser's archives have been held by the Academy of Media Arts in Cologne and are currently housed at the Berlin University of the Arts. === Philosophy of photography === Writing about photography in the 1970s and 80s, in the face of the early worldwide impact of computer technologies, Flusser argued that the photograph was the first in a number of technical image forms to have fundamentally changed the way in which the world is seen. Historically, the importance of photography had been that it introduced nothing less than a new epoch: 'The invention of photography constitutes a break in history that can only be understood in comparison to that other historical break constituted by the invention of linear writing.' Whereas ideas might previously have been interpreted in terms of their written form, photography heralded new forms of perceptual experience and knowledge. As Flusser Archive Supervisor Claudia Becker describes, "For Flusser, photography is not only a reproductive imaging technology, it is a dominant cultural technique through which reality is constituted and understood". In this context, Flusser argued that photographs have to be understood in strict separation from 'pre-technical image forms'. For example, he contrasted them to paintings which he described as images that can be sensibly 'decoded', because the viewer is able to interpret what he or she sees as more or less direct signs of what the painter intended. By contrast, even though photography produces images that seem to be 'faithful reproductions' of objects and events they cannot be so directly 'decoded'. The crux of this difference stems, for Flusser, from the fact that photographs are produced through the operations of an apparatus. And the photographic apparatus operates in ways that are not immediately known or shaped by its operator. For example, he described the act of photographing as follows: The photographer's gesture as the search for a viewpoint onto a scene takes place within the possibilities offered by the apparatus. The photographer moves within specific categories of space and time regarding the scene: proximity and distance, bird- and worm's-eye views, frontal- and side-views, short or long exposures, etc. The Gestalt of space–time surrounding the scene is prefigured for the photographer by the categories of his camera. These categories are an a priori for him. He must 'decide' within them: he must press the trigger. Roughly put, the person using a camera might think that they are operating its controls to produce a picture that shows the world the way they want it to be seen, but it is the pre-programmed character of the camera that sets the parameters of this act and it is the apparatus that shapes the meaning of the resulting image. Given the central role of photography to almost all aspects of contemporary life, the programmed character of the photographic apparatus shapes the experience of looking at and interpreting photographs as well as most of the cultural contexts in which we do so. Flusse

    Read more →
  • WYSIWYM (interaction technique)

    WYSIWYM (interaction technique)

    What you see is what you meant (WYSIWYM) is a text editing interaction technique that emerged from two projects at University of Brighton. It allows users to create abstract knowledge representations such as those required by the Semantic Web using a natural language interface. Natural language understanding (NLU) technology is not employed. Instead, natural language generation (NLG) is used in a highly interactive manner. The text editor accepts repeated refinement of a selected span of text as it becomes progressively less vacuous of authored semantics. Using a mouse, a text property held in the evolving text can be further refined by a set of options derived by NLG from a built-in ontology. An invisible representation of the semantic knowledge is created which can be used for multilingual document generation, formal knowledge formation, or any other task that requires formally specified information. The two projects at Brighton worked in the field of Conceptual Authoring to lay a foundation for further research and development of a Semantic Web Authoring Tool (SWAT). This tool has been further explored as a means for developing a knowledge base by those without prior experience with Controlled Natural Language tools.

    Read more →
  • ELMo

    ELMo

    ELMo (embeddings from language model) is a word embedding method for representing a sequence of words as a corresponding sequence of vectors. It was created by researchers at the Allen Institute for Artificial Intelligence, and University of Washington and first released in February 2018. It is a bidirectional LSTM which takes character-level as inputs and produces word-level embeddings, trained on a corpus of about 30 million sentences and 1 billion words. The architecture of ELMo accomplishes a contextual understanding of tokens. Deep contextualized word representation is useful for many natural language processing tasks, such as coreference resolution and polysemy resolution. ELMo was historically important as a pioneer of self-supervised generative pretraining followed by fine-tuning, where a large model is trained to reproduce a large corpus, then the large model is augmented with additional task-specific weights and fine-tuned on supervised task data. It was an instrumental step in the evolution towards transformer-based language modelling. == Architecture == ELMo is a multilayered bidirectional LSTM on top of a token embedding layer. The output of all LSTMs concatenated together consists of the token embedding. The input text sequence is first mapped by an embedding layer into a sequence of vectors. Then two parts are run in parallel over it. The forward part is a 2-layered LSTM with 4096 units and 512 dimension projections, and a residual connection from the first to second layer. The backward part has the same architecture, but processes the sequence back-to-front. The outputs from all 5 components (embedding layer, two forward LSTM layers, and two backward LSTM layers) are concatenated and multiplied by a linear matrix ("projection matrix") to produce a 512-dimensional representation per input token. ELMo was pretrained on a text corpus of 1 billion words. The forward part is trained by repeatedly predicting the next token, and the backward part is trained by repeatedly predicting the previous token. After the ELMo model is pretrained, its parameters are frozen, except for the projection matrix, which can be fine-tuned to minimize loss on specific language tasks. This is an early example of the pretraining-fine-tune paradigm. The original paper demonstrated this by improving state of the art on six benchmark NLP tasks. === Contextual word representation === The architecture of ELMo accomplishes a contextual understanding of tokens. For example, the first forward LSTM of ELMo would process each input token in the context of all previous tokens, and the first backward LSTM would process each token in the context of all subsequent tokens. The second forward LSTM would then incorporate those to further contextualize each token. Deep contextualized word representation is useful for many natural language processing tasks, such as coreference resolution and polysemy resolution. For example, consider the sentenceShe went to the bank to withdraw money.In order to represent the token "bank", the model must resolve its polysemy in context. The first forward LSTM would process "bank" in the context of "She went to the", which would allow it to represent the word to be a location that the subject is going towards. The first backward LSTM would process "bank" in the context of "to withdraw money", which would allow it to disambiguate the word as referring to a financial institution. The second forward LSTM can then process "bank" using the representation vector provided by the first backward LSTM, thus allowing it to represent it to be a financial institution that the subject is going towards. == Historical context == ELMo is one link in a historical evolution of language modelling. Consider a simple problem of document classification, where we want to assign a label (e.g., "spam", "not spam", "politics", "sports") to a given piece of text. The simplest approach is the "bag of words" approach, where each word in the document is treated independently, and its frequency is used as a feature for classification. This was computationally cheap but ignored the order of words and their context within the sentence. GloVe and Word2Vec built upon this by learning fixed vector representations (embeddings) for words based on their co-occurrence patterns in large text corpora. Like BERT (but unlike "bag of words" such as Word2Vec and GloVe), ELMo word embeddings are context-sensitive, producing different representations for words that share the same spelling. It was trained on a corpus of about 30 million sentences and 1 billion words. Previously, bidirectional LSTM was used for contextualized word representation. ELMo applied the idea to a large scale, achieving state of the art performance. After the 2017 publication of Transformer architecture, the architecture of ELMo was changed from a multilayered bidirectional LSTM to a Transformer encoder, giving rise to BERT. BERT has a similar pretrain-fine-tune workflow, but uses a Transformer with implications for more parallelizable training.

    Read more →
  • Learning rule

    Learning rule

    An artificial neural network's learning rule or learning process is a method, mathematical logic or algorithm which improves the network's performance and/or training time. Usually, this rule is applied repeatedly over the network. It is done by updating the weight and bias levels of a network when it is simulated in a specific data environment. A learning rule may accept existing conditions (weights and biases) of the network, and will compare the expected result and actual result of the network to give new and improved values for the weights and biases. Depending on the complexity of the model being simulated, the learning rule of the network can be as simple as an XOR gate or mean squared error, or as complex as the result of a system of differential equations. The learning rule is one of the factors which decides how fast or how accurately the neural network can be developed. Depending on the process to develop the network, there are three main paradigms of machine learning: supervised learning, unsupervised learning, and reinforcement learning. == Background == A lot of the learning methods in machine learning work similar to each other, and are based on each other, which makes it difficult to classify them in clear categories. But they can be broadly understood in 4 categories of learning methods, though these categories don't have clear boundaries and they tend to belong to multiple categories of learning methods - Hebbian - Neocognitron, Brain-state-in-a-box Gradient Descent - ADALINE, Hopfield Network, Recurrent Neural Network Competitive - Learning Vector Quantisation, Self-Organising Feature Map, Adaptive Resonance Theory Stochastic - Boltzmann Machine, Cauchy Machine Though these learning rules might appear to be based on similar ideas, they do have subtle differences, as they are a generalisation or application over the previous rule, and hence it makes sense to study them separately based on their origins and intents. === Hebbian Learning === Developed by Donald Hebb in 1949 to describe biological neuron firing. In the mid-1950s it was also applied to computer simulations of neural networks. Δ w i = η x i y {\displaystyle \Delta w_{i}=\eta x_{i}y} Where η {\displaystyle \eta } represents the learning rate, x i {\displaystyle x_{i}} represents the input of neuron i, and y is the output of the neuron. It has been shown that Hebb's rule in its basic form is unstable. Oja's Rule, BCM Theory are other learning rules built on top of or alongside Hebb's Rule in the study of biological neurons. ==== Perceptron Learning Rule (PLR) ==== The perceptron learning rule originates from the Hebbian assumption, and was used by Frank Rosenblatt in his perceptron in 1958. The net is passed to the activation (transfer) function and the function's output is used for adjusting the weights. The learning signal is the difference between the desired response and the actual response of a neuron. The step function is often used as an activation function, and the outputs are generally restricted to -1, 0, or 1. The weights are updated with w new = w old + η ( t − o ) x i {\displaystyle w_{\text{new}}=w_{\text{old}}+\eta (t-o)x_{i}} where "t" is the target value and "o" is the output of the perceptron, and η {\displaystyle \eta } is called the learning rate. The algorithm converges to the correct classification if: the training data is linearly separable η {\displaystyle \eta } is sufficiently small (though smaller η {\displaystyle \eta } generally means a longer learning time and more epochs) It should also be noted that a single layer perceptron with this learning rule is incapable of working on linearly non-separable inputs, and hence the XOR problem cannot be solved using this rule alone === Backpropagation === Seppo Linnainmaa in 1970 is said to have developed the Backpropagation Algorithm but the origins of the algorithm go back to the 1960s with many contributors. It is a generalisation of the least mean squares algorithm in the linear perceptron and the Delta Learning Rule. It implements gradient descent search through the space possible network weights, iteratively reducing the error, between the target values and the network outputs. ==== Widrow-Hoff Learning (Delta Learning Rule) ==== Similar to the perceptron learning rule but with different origin. It was developed for use in the ADALINE network, which differs from the Perceptron mainly in terms of the training. The weights are adjusted according to the weighted sum of the inputs (the net), whereas in perceptron the sign of the weighted sum was useful for determining the output as the threshold was set to 0, -1, or +1. This makes ADALINE different from the normal perceptron. Delta rule (DR) is similar to the Perceptron Learning Rule (PLR), with some differences: Error (δ) in DR is not restricted to having values of 0, 1, or -1 (as in PLR), but may have any value DR can be derived for any differentiable output/activation function f, whereas in PLR only works for threshold output function Sometimes only when the Widrow-Hoff is applied to binary targets specifically, it is referred to as Delta Rule, but the terms seem to be used often interchangeably. The delta rule is considered to a special case of the back-propagation algorithm. Delta rule also closely resembles the Rescorla-Wagner model under which Pavlovian conditioning occurs. === Competitive Learning === Competitive learning is considered a variant of Hebbian learning, but it is special enough to be discussed separately. Competitive learning works by increasing the specialization of each node in the network. It is well suited to finding clusters within data. Models and algorithms based on the principle of competitive learning include vector quantization and self-organizing maps (Kohonen maps).

    Read more →
  • HiLog

    HiLog

    HiLog is a programming logic with higher-order syntax, which allows arbitrary terms to appear in predicate and function positions. However, the model theory of HiLog is first-order. Although syntactically HiLog strictly extends first order logic, HiLog can be embedded into this logic. HiLog was first described in 1989. It was later extended in the direction of many-sorted logic. The XSB system parses HiLog syntax, but the integration of HiLog into XSB is only partial. In particular, HiLog is not integrated with the XSB module system. A full implementation of HiLog is available in the Flora-2 system. It has been shown that HiLog can be embedded into first-order logic through a fairly simple transformation. For instance, p(X)(Y,Z(V)(W)) gets embedded as the following first-order term: apply(p(X),Y,apply(apply(Z,V),W)). The Framework for Logic-Based Dialects (RIF-FLD) of the Rule Interchange Format (RIF) is largely based on the ideas underlying HiLog and F-logic. == Examples == In all the examples below, capitalized symbols denote variables and the comma denotes logical conjunction, as in most logic programming languages. The first and the second examples show that variables can appear in predicate positions. Predicates can even be complex terms, such as closure(P) or maplist(F) below. The third example shows that variables can also appear in place of atomic formulas, while the fourth example illustrates the use of variables in place of function symbols. The first example defines a generic transitive closure operator, which can be applied to an arbitrary binary predicate. The second example is similar. It defines a LISP-like mapping operator, which applies to an arbitrary binary predicate. The third example shows that the Prolog meta-predicate call/1 can be expressed in HiLog in a natural way and without the use of extra-logical features. The last example defines a predicate that traverses arbitrary binary trees represented as first-order terms.

    Read more →