Neuro-symbolic AI is a subfield of artificial intelligence that integrates neural methods (e.g., neural networks and deep learning) with symbolic methods (e.g., formal logic, knowledge representation, and automated reasoning). The goal is to combine the strengths of both approaches, resulting in AI systems that can be trained from raw data and demonstrate robustness against outliers or errors in the base data, while preserving explainability, explicit use of expert knowledge, and explicit cognitive reasoning. As argued by Leslie Valiant and others, the effective construction of rich computational cognitive models demands the combination of symbolic reasoning and efficient machine learning. Gary Marcus argued, "We cannot construct rich cognitive models in an adequate, automated way without the triumvirate of hybrid architecture, rich prior knowledge, and sophisticated techniques for reasoning." Further, "To build a robust, knowledge-driven approach to AI we must have the machinery of symbol manipulation in our toolkit. Too much of useful knowledge is abstract to make do without tools that represent and manipulate abstraction, and to date, the only known machinery that can manipulate such abstract knowledge reliably is the apparatus of symbol manipulation." Angelo Dalli, Henry Kautz, Francesca Rossi, and Bart Selman also argued for such a synthesis. Their arguments attempt to address the two kinds of thinking, as discussed in Daniel Kahneman's book Thinking, Fast and Slow. It describes cognition as encompassing two components: System 1 is fast, reflexive, intuitive, and unconscious. System 2 is slower, step-by-step, and explicit. System 1 is used for pattern recognition. System 2 handles planning, deduction, and deliberative thinking. In this view, deep learning best handles the first kind of cognition, while symbolic reasoning best handles the second kind. Both are necessary for the development of a robust and reliable AI system capable of learning, reasoning, and interacting with humans to accept advice and answer questions. Since the 1990s, dual-process models with explicit references to the two contrasting systems have been the focus of research in both the fields of AI and cognitive science by numerous researchers. In 2025, the adoption of neurosymbolic AI, an approach that integrates neural networks with symbolic reasoning, increased in response to the need to address hallucination issues in large language models. For example, Amazon implemented Neurosymbolic AI in its Vulcan warehouse robots and Rufus shopping assistant to enhance accuracy and decision-making. == Approaches == Approaches for integration are diverse. Henry Kautz's taxonomy of neuro-symbolic architectures follows, along with some examples: Symbolic Neural symbolic is the current approach of many neural models in natural language processing, where words or subword tokens are the ultimate input and output of large language models. Examples include BERT, RoBERTa, and GPT-3. Symbolic[Neural] is exemplified by AlphaGo, where symbolic techniques are used to invoke neural techniques. In this case, the symbolic approach is Monte Carlo tree search and the neural techniques learn how to evaluate game positions. Neural | Symbolic uses a neural architecture to interpret perceptual data as symbols and relationships that are reasoned about symbolically. Neural-Concept Learner is an example. Neural: Symbolic → Neural relies on symbolic reasoning to generate or label training data that is subsequently learned by a deep learning model, e.g., to train a neural model for symbolic computation by using a Macsyma-like symbolic mathematics system to create or label examples. NeuralSymbolic uses a neural net that is generated from symbolic rules. An example is the Neural Theorem Prover, which constructs a neural network from an AND-OR proof tree generated from knowledge base rules and terms. Logic Tensor Networks also fall into this category. Neural[Symbolic] according to Kautz, this approach embeds true symbolic reasoning inside a neural network. These are tightly-coupled neural-symbolic systems, in which the logical inference rules are internal to the neural network. This way, the neural network internally computes the inference from the premises and learns to reason based on logical inference systems. Early work on connectionist modal and temporal logics by Garcez, Lamb, and Gabbay is aligned with this approach. These categories are not exhaustive, as they do not consider multi-agent systems. In 2005, Bader and Hitzler presented a more fine-grained categorization that took into account, e.g., whether the use of symbols included logic and, if so, whether the logic was propositional or first-order logic. The 2005 categorization and Kautz's taxonomy above are compared and contrasted in a 2021 article. Sepp Hochreiter argued that Graph Neural Networks "...are the predominant models of neural-symbolic computing" since "[t]hey describe the properties of molecules, simulate social networks, or predict future states in physical and engineering applications with particle-particle interactions." == Artificial general intelligence == Gary Marcus argues that "...hybrid architectures that combine learning and symbol manipulation are necessary for robust intelligence, but not sufficient", and that there are ...four cognitive prerequisites for building robust artificial intelligence: hybrid architectures that combine large-scale learning with the representational and computational powers of symbol manipulation, large-scale knowledge bases—likely leveraging innate frameworks—that incorporate symbolic knowledge along with other forms of knowledge, reasoning mechanisms capable of leveraging those knowledge bases in tractable ways, and rich cognitive models that work together with those mechanisms and knowledge bases. This echoes earlier calls for hybrid models as early as the 1990s. == History == Garcez and Lamb described research in this area as ongoing, at least since the 1990s. During that period, the terms symbolic and sub-symbolic AI were popular. A series of workshops on neuro-symbolic AI has been held annually since 2005 Neuro-Symbolic Artificial Intelligence. In the early 1990s, an initial set of workshops on this topic were organized. == Research == Key research questions remain, such as: What is the best way to integrate neural and symbolic architectures? How should symbolic structures be represented within neural networks and extracted from them? How should common-sense knowledge be learned and reasoned about? How can abstract knowledge that is hard to encode logically be handled? == Implementations == Implementations of neuro-symbolic approaches include: AllegroGraph: an integrated Knowledge Graph based platform for neuro-symbolic application development. Scallop: a language based on Datalog that supports differentiable logical and relational reasoning. Scallop can be integrated in Python and with a PyTorch learning module. Logic Tensor Networks: encode logical formulas as neural networks and simultaneously learn term encodings, term weights, and formula weights. DeepProbLog: combines neural networks with the probabilistic reasoning of ProbLog. Abductive Learning: integrates machine learning and logical reasoning in a balanced-loop via abductive reasoning, enabling them to work together in a mutually beneficial way. SymbolicAI: a compositional differentiable programming library.
System context diagram
A system context diagram in engineering is a diagram that defines the boundary between the system, or part of a system, and its environment, showing the entities that interact with it. This diagram is a high level view of a system. It is similar to a block diagram. == Overview == System context diagrams show a system, as a whole and its inputs and outputs from/to external factors. According to Kossiakoff and Sweet (2011): System Context Diagrams ... represent all external entities that may interact with a system ... Such a diagram pictures the system at the center, with no details of its interior structure, surrounded by all its interacting systems, environments and activities. The objective of the system context diagram is to focus attention on external factors and events that should be considered in developing a complete set of systems requirements and constraints. System context diagrams are used early in a project to get agreement on the scope under investigation. Context diagrams are typically included in a requirements document. These diagrams must be read by all project stakeholders and thus should be written in plain language, so the stakeholders can understand items within the document. == Building blocks == Context diagrams can be developed with the use of two types of building blocks: Entities (Actors): labeled boxes; one in the center representing the system, and around it multiple boxes for each external actor Relationships: labeled lines between the entities and system For example, "customer places order." Context diagrams can also use many different drawing types to represent external entities. They can use ovals, stick figures, pictures, clip art or any other representation to convey meaning. Decision trees and data storage are represented in system flow diagrams. A context diagram can also list the classifications of the external entities as one of a set of simple categories (Examples:), which add clarity to the level of involvement of the entity with regards to the system. These categories include: Active: Dynamic to achieve some goal or purpose (Examples: "Article readers" or "customers"). Passive: Static external entities which infrequently interact with the system (Examples: "Article editors" or "database administrator"). Cooperative: Predictable external entities which are used by the system to bring about some desired outcome (Examples: "Internet service providers" or "shipping companies"). Autonomous (Independent): External entities which are separated from the system, but affect the system indirectly, by means of imposed constraints or similar influences (Examples: "regulatory committees" or "standards groups"). == Alternatives == The best system context diagrams are used to display how a system interoperates at a very high level, or how systems operate and interact logically. The system context diagram is a necessary tool in developing a baseline interaction between systems and actors; actors and a system or systems and systems. Alternatives to the system context diagram are: Architecture Interconnect Diagram: The figure gives an example of an Architecture Interconnect Diagram: A representation of the Albuquerque regional ITS architecture interconnects for the Albuquerque Police Department that was generated using the Turbo Architecture tool is shown in the figure. Each block represents an ITS inventory element, including the name of the stakeholder in the top shaded portion. The interconnect lines between elements are solid or dashed, indicating existing or planned connections. Business Model Canvas, a strategic management template for developing new or documenting existing business models. It is a visual chart with elements describing a firm's value proposition, infrastructure, customers, and finances.[1] It assists firms in aligning their activities by illustrating potential trade-offs. Enterprise data model: this type of data model according to Simsion (2005) can contain up to 50 to 200 entity classes, which results from specific "high level of generalization in data modeling". IDEF0 Top Level Context Diagram: The IDEF0 process starts with the identification of the prime function to be decomposed. This function is identified on a "Top Level Context Diagram" that defines the scope of the particular IDEF0 analysis. Problem Diagrams (Problem Frames): In addition to the kinds of things shown on a context diagram, a problem diagram shows requirements and requirements references. Use case diagram: One of the Unified Modeling Language diagrams. They also represent the scope of the project at a similar level of abstraction. - Use Cases, however, tend to focus more on the goals of 'actors' who interact with the system, and do not specify any solution. Use Case diagrams represent a set of Use Cases, which are textual descriptions of how an actor achieves the goal of a use case. for Example Customer Places Order. ArchiMate: ArchiMate is an open and independent enterprise architecture modeling language to support the description, analysis and visualization of architecture within and across business domains in an unambiguous way. Most of these diagrams work well as long as a limited number of interconnects will be shown. Where twenty or more interconnects must be displayed, the diagrams become quite complex and can be difficult to read.
Information Processing Language
Information Processing Language (IPL) is a programming language created by Allen Newell, Cliff Shaw, and Herbert A. Simon at RAND Corporation and the Carnegie Institute of Technology about 1956. Newell had the job of language specifier-application programmer, Shaw was the system programmer, and Simon had the job of application programmer-user. IPL included features to facilitate AI programming, specifically problem solving. such as lists, dynamic memory allocation, data types, recursion, functions as arguments, generators, and cooperative multitasking. IPL also introduced the concepts of symbol processing and list processing. Unfortunately, all of these innovations were cast in a difficult assembly-language style. Nonetheless, IPL-V (the only public version of IPL) ran on many computers through the mid 1960s. == Basics of IPL == An IPL computer has: A set of symbols. All symbols are addresses, and name cells. Unlike symbols in later languages, symbols consist of a character followed by a number, and are written H1, A29, 9–7, 9–100. Cell names beginning with a letter are regional, and are absolute addresses. Cell names beginning with "9-" are local, and are meaningful within the context of a single list. One list's 9-1 is independent of another list's 9–1. Other symbols (e.g., pure numbers) are internal. A set of cells. Lists are made from several cells including mutual references. Cells have several fields: P, a 3-bit field used for an operation code when the cell is used as an instruction, and unused when the cell is data. Q, a 3-valued field used for indirect reference when the cell is used as an instruction, and unused when the cell is data. SYMB, a symbol used as the value in the cell. A set of primitive processes, which would be termed primitive functions in modern languages. The data structure of IPL is the list, but lists are more intricate structures than in many languages. A list consists of a singly linked sequence of symbols, as might be expected—plus some description lists, which are subsidiary singly linked lists interpreted as alternating attribute names and values. IPL provides primitives to access and mutate attribute value by name. The description lists are given local names (of the form 9–1). So, a list named L1 containing the symbols S4 and S5, and described by associating value V1 to attribute A1 and V2 to A2, would be stored as follows. 0 indicates the end of a list; the cell names 100, 101, etc. are automatically generated internal symbols whose values are irrelevant. These cells can be scattered throughout memory; only L1, which uses a regional name that must be globally known, needs to reside in a specific place. IPL is an assembly language for manipulating lists. It has a few cells which are used as special-purpose registers. H1, for example, is the program counter. The SYMB field of H1 is the name of the current instruction. However, H1 is interpreted as a list; the LINK of H1 is, in modern terms, a pointer to the beginning of the call stack. For example, subroutine calls push the SYMB of H1 onto this stack. H2 is the free-list. Procedures which need to allocate memory grab cells off of H2; procedures which are finished with memory put it on H2. On entry to a function, the list of parameters is given in H0; on exit, the results should be returned in H0. Many procedures return a Boolean result indicating success or failure, which is put in H5. Ten cells, W0-W9, are reserved for public working storage. Procedures are "morally bound" (to quote the CACM article) to save and restore the values of these cells. There are eight instructions, based on the values of P: subroutine call, push/pop S to H0; push/pop the symbol in S to the list attached to S; copy value to S; conditional branch. In these instructions, S is the target. S is either the value of the SYMB field if Q=0, the symbol in the cell named by SYMB if Q=1, or the symbol in the cell named by the symbol in the cell named by SYMB if Q=2. In all cases but conditional branch, the LINK field of the cell tells which instruction to execute next. IPL has a library of some 150 basic operations. These include such operations as: Test symbols for equality Find, set, or erase an attribute of a list Locate the next symbol in a list; insert a symbol in a list; erase or copy an entire list Arithmetic operations (on symbol names) Manipulation of symbols; e.g., test if a symbol denotes an integer, or make a symbol local I/O operations "Generators", which correspond to iterators and filters in functional programming. For example, a generator may accept a list of numbers and produce the list of their squares. Generators could accept suitably designed functions—strictly, the addresses of code of suitably designed functions—as arguments. == History == IPL was first utilized to demonstrate that the theorems in Principia Mathematica which were proven laboriously by hand, by Bertrand Russell and Alfred North Whitehead, could in fact be proven by computation. According to Simon's autobiography Models of My Life, this application was originally developed first by hand simulation, using his children as the computing elements, while writing on and holding up note cards as the registers which contained the state variables of the program. IPL was used to implement several early artificial intelligence programs, also by the same authors: the Logic Theorist (1956), the General Problem Solver (1957), and their computer chess program NSS (1958). Several versions of IPL were created: IPL-I (never implemented), IPL-II (1957 for JOHNNIAC), IPL-III (existed briefly), IPL-IV, IPL-V (1958, for IBM 650, IBM 704, IBM 7090, Philco model 212, many others. Widely used). IPL-VI was a proposal for an IPL hardware. A co-processor “IPL-VC” for the CDC 3600 at Argonne National Libraries was developed which could run IPL-V commands. It was used to implement another checker-playing program. This hardware implementation did not improve running times sufficiently to “compete favorably with a language more directly oriented to the structure of present-day machines”. IPL was soon displaced by Lisp, which had much more powerful features, a simpler syntax, and the benefit of automatic garbage collection. == Legacy to computer programming == IPL arguably introduced several programming language features: List manipulation—but only lists of atoms, not general lists Property lists—but only when attached to other lists Higher-order functions—while assembly programming had always allowed computing with the addresses of functions, IPL was an early attempt to generalize this property of assembly language in a principled way Computation with symbols—though symbols have a restricted form in IPL (letter followed by number) Virtual machine Many of these features were generalized, rationalized, and incorporated into Lisp and from there into many other programming languages during the next several decades.
ChipTest
ChipTest was a 1985 chess playing computer built by Feng-hsiung Hsu, Thomas Anantharaman and Murray Campbell at Carnegie Mellon University. It is the predecessor of Deep Thought which in turn evolved into Deep Blue. == History == ChipTest was based on a special VLSI-technology move generator chip developed by Hsu. ChipTest was controlled by a Sun-3/160 workstation and capable of searching approximately 50,000 moves per second. Hsu and Anantharaman entered ChipTest in the 1986 North American Computer Chess Championship, and it was only partially tested when the tournament began. It lost its first two rounds, but finished with an even score. In August 1987, ChipTest was overhauled and renamed ChipTest-M, M standing for microcode. The new version had eliminated ChipTest's bugs and was ten times faster, searching 500,000 moves per second and running on a Sun-4 workstation. ChipTest-M won the North American Computer Chess Championship in 1987 with a 4–0 sweep. ChipTest was invited to play in the 1987 American Open, but the team did not enter due to an objection by the HiTech team, also from Carnegie Mellon University. HiTech and ChipTest shared some code, and Hitech was already playing in the tournament. The two teams became rivals. Designing and implementing ChipTest revealed many possibilities for improvement, so the designers started on a new machine. Deep Thought 0.01 was created in May 1988 and the version 0.02 in November the same year. This new version had two customized VLSI chess processors and it was able to search 720,000 moves per second. With the "0.02" dropped from its name, Deep Thought won the World Computer Chess Championship with a perfect 5–0 score in 1989.
Computational Intelligence (journal)
Computational Intelligence Journal is a peer-reviewed scientific journal covering research on artificial intelligence and computer science. The journal published novel research as well as innovative applications in a broad range of AI, covering Computational Intelligence is an artificial intelligence journal publishing novel research on a broad range of experimental and theoretical topics in AI and computer science. With a broad scope, the journal covers machine learning, knowledge mining, web intelligence, AI language, and philosophical implications. The journal was established in 1985 and is published by Wiley-Blackwell. Currently, the editors-in-chief is Diane Inkpen. The quality of the journal as an academic publishing venue is evaluated according to public citation impact metrics. in 2022, the Computational Intelligence Journal CiteScore of Scopus was 5.3, while Clarivate's Web of Science gives it 0.39 in the Journal Citation Indicator and 2,8 in the Journal Impact Factor.
Kindara
Kindara is a femtech company headquartered in Colorado that develops apps that help women identify their fertile window. The products are used for women trying to get pregnant, or women who want to track their menstrual cycle for overall health. Their latest product, Priya Fertility and Ovulation Monitor, maximizes a woman's chance of getting pregnancy by identifying her most fertile days. == Overview == Kindara was founded in 2011 by husband-and-wife team Will Sacks and Kati Bicknell. The company launched its free mobile application in 2012. Kindara's mobile application allows women to track signs of fertility, such as basal body temperature, cervical fluid, and the position of the cervix to determine when ovulation is occurring. Kindara also sells a thermometer, Wink, which records basal body temperature and syncs automatically to the Kindara fertility application. In 2018, Kindara was acquired by the company Prima-Temp.
Computer game bot Turing test
The computer game bot Turing test is a variant of the Turing test, where a human judge viewing and interacting with a virtual world must distinguish between other humans and video game bots, both interacting with the same virtual world. This variant was first proposed in 2008 by Associate Professor Philip Hingston of Edith Cowan University, and implemented through a tournament called the 2K BotPrize. == History == The computer game bot Turing test was proposed to advance the fields of artificial intelligence (AI) and computational intelligence with respect to video games. It was considered that a poorly implemented bot implied a subpar game, so a bot that would be capable of passing this test, and therefore might be indistinguishable from a human player, would directly improve the quality of a game. It also served to debunk a flawed notion that "game AI is a solved problem." Emphasis is placed on a game bot that interacts with other players in a multiplayer environment. Unlike a bot that simply needs to make optimal human-like decisions to play or beat a game, this bot must make the same decisions while also convincing another in-game player of its human-likeness. == Implementation == The computer game bot Turing test was designed to test a bot's ability to interact with a game environment in comparison with a human player; simply 'winning' was insufficient. This evolved into a contest with a few important goals in mind: There are three participants: a human player, a computer-game bot, and a judge. The bot needs to appear more human-like than the human player. Judge scores are not bipolar — both human and bot can be scored anywhere on a scale from 1 to 5 (1=not humanlike, 5=human). All three participants are to be indistinguishable in the arena, with the exception of a randomly generated name tag, so as to reduce the chance of random elements such as name or appearance influencing the judges. Chat is disabled throughout the match. Bots were not given omniscient powers as they may be in other games. Bots must react only to the data that might be reasonably available to a human player. Human participants were of a moderate skill range, with no participant either ignorant to the game or capable of playing at a professional level. In 2008, the first 2K BotPrize tournament took place. The contest was held with the game Unreal Tournament 2004 as the platform. Contestants created their bots in advance using the GameBots interface. GameBots had some modifications made so as to adhere to the above conditions, such as removing data about vantage points or weapon damage that unfairly informed the bots of relevant strengths/weaknesses that a human would otherwise need to learn. == Tournament == The first BotPrize Tournament was held on 17 December 2008, as part of the 2008 IEEE Symposium on Computational Intelligence and Games in Australia. Each competing team was given time to set up and adjust their bots to the modified game client, although no coding changes were allowed at that point. The tournament was run in rounds, each a 10-minute death match. Judges were the last to join the server and every judge observed every player and every bot exactly once, although the pairing of players and bots did change. When the tournament ended, no bot was rated as more human than any player. In subsequent tournaments, run during 2009–2011, bots achieved scores that were increasingly human-like, but no contestant had won the BotPrize in any of these contests. In 2012, the 2K BotPrize was held once again, and two teams programmed bots that achieved scores greater than those of human players. == Successful bots == To date, there have been two successfully programmed bots that passed the computer game bot Turing test: UT^2, a team from the University of Texas at Austin, emphasized a bot that adjusted its behaviour based on previously observed human behaviour and neuroevolution. The team has made their bot available, although a copy of Unreal Tournament 2004 is required. Mihai Polceanu, a doctoral student from Romania, focused on creating a bot that would mimic opponent reactions, in a sense 'borrowing' the human-like nature of the opponent. These victors succeeded in the year 2012, Alan Turing's centenary year. == Aftermath == The outcome of a bot that appears more human-like than a human player is possibly overstated, since in the tournament in which the bots succeeded, the average 'humanness' rating of the human players was only 41.4%. This showcases some limits of this Turing test, since the results demonstrate that human behaviour is more complicated and quantitative than was accounted for. In light of this, the BotPrize competition organizers will increase the difficulty in upcoming years with new challenges, forcing competitors to improve their bots. It is also believed that methods and techniques developed for the computer game bot Turing test will be useful in fields other than video games, such as virtual training environments and in improving Human–robot interaction. == Contrasts to the Turing test == The computer game bot Turing test differs from the traditional or generic Turing test in a number of ways: Unlike the traditional Turing test, for example the Chatterbot-style contest held annually by the Loebner Prize competition, the humans who played against the Computer Game Bots are not trying to convince judges they are the human; rather, they want to win the game (i.e., by achieving the highest kill score). Judges are not restricted to awarding only one participant in a match as the 'human' and the other as the 'non-human.' This emphasizes more qualitative rather than polarized findings. With regards to a successful video game bot, this is not to be confused with a claim that the bot is 'intelligent,' whereas a machine that 'passed' the Turing test would arguably have some evidence for its Chatterbot's 'intelligence.' The game Unreal Tournament 2004 was chosen for its commercial availability and its interface for creating bots, GameBots. This limitation on medium is a sharp contrast to the Turing test, which emphasizes a conversation, where possible questions are vastly more numerous than the set of possible actions available in any specific video game. The available information to the participants, humans and bots, is not equal. Humans interact through vision and sound, whereas bots interact with data and events. The judges cannot introduce new events (e.g., a lava pit) to aid in differentiating between human and bot, whereas in a Chatterbot designed system, judges may theoretically ask any question in any manner. The two participants and the judge take part in a three-way interaction, unlike, for example, the paired two-way interaction of the Loebner Prize Contest.