Vue d'ensemble

  • Missions postés 0

Description de l'entreprise

Symbolic Expert System

In synthetic intelligence, symbolic artificial intelligence (also called classical synthetic intelligence or logic-based artificial intelligence) [1] [2] is the term for the collection of all approaches in expert system research study that are based upon top-level symbolic (human-readable) representations of issues, reasoning and search. [3] Symbolic AI utilized tools such as logic shows, production rules, semantic webs and frames, and it developed applications such as knowledge-based systems (in specific, expert systems), symbolic mathematics, automated theorem provers, ontologies, the semantic web, and automated planning and scheduling systems. The Symbolic AI paradigm resulted in critical concepts in search, symbolic programming languages, representatives, multi-agent systems, the semantic web, and the strengths and constraints of official knowledge and reasoning systems.

Symbolic AI was the dominant paradigm of AI research from the mid-1950s till the mid-1990s. [4] Researchers in the 1960s and the 1970s were convinced that symbolic approaches would ultimately prosper in producing a maker with synthetic general intelligence and considered this the ultimate goal of their field. [citation needed] An early boom, with early successes such as the Logic Theorist and Playing Program, resulted in impractical expectations and promises and was followed by the first AI Winter as funding dried up. [5] [6] A 2nd boom (1969-1986) took place with the increase of professional systems, their guarantee of catching business knowledge, and a passionate corporate embrace. [7] [8] That boom, and some early successes, e.g., with XCON at DEC, was followed again by later disappointment. [8] Problems with difficulties in knowledge acquisition, keeping big understanding bases, and brittleness in managing out-of-domain issues emerged. Another, 2nd, AI Winter (1988-2011) followed. [9] Subsequently, AI researchers concentrated on attending to hidden problems in managing uncertainty and in understanding acquisition. [10] Uncertainty was addressed with formal methods such as surprise Markov models, Bayesian thinking, and analytical relational learning. [11] [12] Symbolic machine finding out dealt with the knowledge acquisition problem with contributions including Version Space, Valiant’s PAC knowing, Quinlan’s ID3 decision-tree learning, case-based learning, and inductive reasoning programming to find out relations. [13]

Neural networks, a subsymbolic approach, had been pursued from early days and reemerged strongly in 2012. Early examples are Rosenblatt’s perceptron knowing work, the backpropagation work of Rumelhart, Hinton and Williams, [14] and work in convolutional neural networks by LeCun et al. in 1989. [15] However, neural networks were not viewed as effective up until about 2012: « Until Big Data ended up being prevalent, the general consensus in the Al community was that the so-called neural-network method was helpless. Systems simply didn’t work that well, compared to other methods. … A revolution was available in 2012, when a number of people, including a team of scientists working with Hinton, worked out a method to utilize the power of GPUs to immensely increase the power of neural networks. » [16] Over the next a number of years, deep knowing had amazing success in dealing with vision, speech acknowledgment, speech synthesis, image generation, and maker translation. However, considering that 2020, as inherent troubles with bias, explanation, comprehensibility, and effectiveness became more apparent with deep learning approaches; an increasing variety of AI scientists have actually required combining the very best of both the symbolic and neural network techniques [17] [18] and resolving areas that both approaches have problem with, such as sensible thinking. [16]

A short history of symbolic AI to the present day follows listed below. Period and titles are drawn from Henry Kautz’s 2020 AAAI Robert S. Engelmore Memorial Lecture [19] and the longer Wikipedia article on the History of AI, with dates and titles differing slightly for increased clearness.

The first AI summer: irrational exuberance, 1948-1966

Success at early attempts in AI occurred in three primary areas: synthetic neural networks, understanding representation, and heuristic search, contributing to high expectations. This area sums up Kautz’s reprise of early AI history.

Approaches inspired by human or animal cognition or habits

Cybernetic techniques attempted to reproduce the feedback loops between animals and their environments. A robotic turtle, with sensors, motors for driving and guiding, and 7 vacuum tubes for control, based on a preprogrammed neural net, was developed as early as 1948. This work can be seen as an early precursor to later work in neural networks, reinforcement knowing, and positioned robotics. [20]

An important early symbolic AI program was the Logic theorist, written by Allen Newell, Herbert Simon and Cliff Shaw in 1955-56, as it was able to show 38 elementary theorems from Whitehead and Russell’s Principia Mathematica. Newell, Simon, and Shaw later generalized this work to create a domain-independent problem solver, GPS (General Problem Solver). GPS solved problems represented with official operators via state-space search using means-ends analysis. [21]

During the 1960s, symbolic methods attained great success at simulating intelligent behavior in structured environments such as game-playing, symbolic mathematics, and theorem-proving. AI research was concentrated in four institutions in the 1960s: Carnegie Mellon University, Stanford, MIT and (later) University of Edinburgh. Each one established its own style of research. Earlier approaches based on cybernetics or artificial neural networks were abandoned or pressed into the background.

Herbert Simon and Allen Newell studied human analytical abilities and tried to formalize them, and their work laid the foundations of the field of expert system, along with cognitive science, operations research and management science. Their research study group utilized the results of psychological experiments to develop programs that simulated the strategies that individuals utilized to solve problems. [22] [23] This custom, centered at Carnegie Mellon University would ultimately culminate in the development of the Soar architecture in the center 1980s. [24] [25]

Heuristic search

In addition to the extremely specialized domain-specific sort of knowledge that we will see later used in expert systems, early symbolic AI researchers found another more general application of knowledge. These were called heuristics, guidelines of thumb that direct a search in appealing instructions: « How can non-enumerative search be useful when the underlying issue is tremendously difficult? The approach advocated by Simon and Newell is to utilize heuristics: fast algorithms that may stop working on some inputs or output suboptimal solutions. » [26] Another important advance was to discover a method to apply these heuristics that ensures an option will be discovered, if there is one, not withstanding the periodic fallibility of heuristics: « The A * algorithm provided a general frame for total and optimum heuristically guided search. A * is utilized as a subroutine within practically every AI algorithm today but is still no magic bullet; its warranty of completeness is bought at the cost of worst-case rapid time. [26]

Early deal with knowledge representation and thinking

Early work covered both applications of formal thinking highlighting first-order reasoning, along with efforts to deal with sensible reasoning in a less formal manner.

Modeling formal reasoning with logic: the « neats »

Unlike Simon and Newell, John McCarthy felt that devices did not require to replicate the precise systems of human thought, but might rather search for the essence of abstract reasoning and analytical with reasoning, [27] no matter whether individuals used the same algorithms. [a] His laboratory at Stanford (SAIL) concentrated on utilizing official reasoning to resolve a wide array of issues, including knowledge representation, preparation and knowing. [31] Logic was also the focus of the work at the University of Edinburgh and somewhere else in Europe which resulted in the advancement of the programs language Prolog and the science of reasoning programming. [32] [33]

Modeling implicit common-sense understanding with frames and scripts: the « scruffies »

Researchers at MIT (such as Marvin Minsky and Seymour Papert) [34] [35] [6] discovered that resolving difficult issues in vision and natural language processing needed ad hoc solutions-they argued that no easy and general concept (like reasoning) would record all the aspects of intelligent behavior. Roger Schank described their « anti-logic » methods as « scruffy » (rather than the « cool » paradigms at CMU and Stanford). [36] [37] Commonsense knowledge bases (such as Doug Lenat’s Cyc) are an example of « shabby » AI, since they should be built by hand, one complex idea at a time. [38] [39] [40]

The first AI winter season: crushed dreams, 1967-1977

The very first AI winter season was a shock:

During the first AI summertime, many individuals thought that device intelligence might be attained in just a few years. The Defense Advance Research Projects Agency (DARPA) released programs to support AI research to use AI to resolve problems of national security; in specific, to automate the translation of Russian to English for intelligence operations and to produce self-governing tanks for the battlefield. Researchers had begun to recognize that attaining AI was going to be much harder than was expected a decade earlier, but a mix of hubris and disingenuousness led numerous university and think-tank scientists to accept financing with promises of deliverables that they must have understood they might not meet. By the mid-1960s neither beneficial natural language translation systems nor self-governing tanks had been developed, and a remarkable reaction set in. New DARPA management canceled existing AI financing programs.

Beyond the United States, the most fertile ground for AI research was the UK. The AI winter in the UK was stimulated on not so much by disappointed military leaders as by rival academics who viewed AI scientists as charlatans and a drain on research study financing. A professor of used mathematics, Sir James Lighthill, was commissioned by Parliament to assess the state of AI research in the country. The report mentioned that all of the issues being worked on in AI would be much better handled by researchers from other disciplines-such as applied mathematics. The report also claimed that AI successes on toy issues might never scale to real-world applications due to combinatorial surge. [41]

The 2nd AI summer: understanding is power, 1978-1987

Knowledge-based systems

As constraints with weak, domain-independent methods ended up being increasingly more evident, [42] scientists from all three traditions started to build understanding into AI applications. [43] [7] The knowledge transformation was driven by the realization that knowledge underlies high-performance, domain-specific AI applications.

Edward Feigenbaum said:

– « In the understanding lies the power. » [44]
to explain that high performance in a specific domain needs both general and highly domain-specific knowledge. Ed Feigenbaum and Doug Lenat called this The Knowledge Principle:

( 1) The Knowledge Principle: if a program is to perform a complicated task well, it must understand a fantastic offer about the world in which it operates.
( 2) A possible extension of that principle, called the Breadth Hypothesis: there are two additional capabilities necessary for intelligent habits in unanticipated circumstances: drawing on increasingly general knowledge, and analogizing to particular however distant knowledge. [45]

Success with expert systems

This « understanding transformation » caused the development and implementation of professional systems (presented by Edward Feigenbaum), the very first commercially effective kind of AI software. [46] [47] [48]

Key expert systems were:

DENDRAL, which discovered the structure of organic particles from their chemical formula and mass spectrometer readings.
MYCIN, which diagnosed bacteremia – and recommended more laboratory tests, when necessary – by analyzing laboratory outcomes, patient history, and doctor observations. « With about 450 rules, MYCIN had the ability to perform as well as some experts, and significantly better than junior doctors. » [49] INTERNIST and CADUCEUS which took on internal medicine medical diagnosis. Internist tried to capture the know-how of the chairman of internal medicine at the University of Pittsburgh School of Medicine while CADUCEUS might ultimately diagnose up to 1000 different illness.
– GUIDON, which demonstrated how an understanding base developed for professional problem fixing could be repurposed for teaching. [50] XCON, to set up VAX computers, a then tiresome procedure that could take up to 90 days. XCON reduced the time to about 90 minutes. [9]
DENDRAL is thought about the very first professional system that relied on knowledge-intensive problem-solving. It is described listed below, by Ed Feigenbaum, from a Communications of the ACM interview, Interview with Ed Feigenbaum:

Among the individuals at Stanford thinking about computer-based models of mind was Joshua Lederberg, the 1958 Nobel Prize winner in genes. When I told him I desired an induction « sandbox », he stated, « I have just the one for you. » His lab was doing mass spectrometry of amino acids. The concern was: how do you go from taking a look at the spectrum of an amino acid to the chemical structure of the amino acid? That’s how we started the DENDRAL Project: I was good at heuristic search approaches, and he had an algorithm that was proficient at generating the chemical problem space.

We did not have a grandiose vision. We worked bottom up. Our chemist was Carl Djerassi, innovator of the chemical behind the contraceptive pill, and likewise among the world’s most respected mass spectrometrists. Carl and his postdocs were world-class professionals in mass spectrometry. We started to contribute to their knowledge, creating knowledge of engineering as we went along. These experiments totaled up to titrating DENDRAL a growing number of understanding. The more you did that, the smarter the program became. We had excellent results.

The generalization was: in the understanding lies the power. That was the big concept. In my profession that is the huge, « Ah ha!, » and it wasn’t the way AI was being done formerly. Sounds simple, but it’s probably AI’s most effective generalization. [51]

The other professional systems discussed above came after DENDRAL. MYCIN exhibits the classic professional system architecture of a knowledge-base of guidelines paired to a symbolic thinking system, consisting of making use of certainty factors to deal with unpredictability. GUIDON reveals how an explicit understanding base can be repurposed for a second application, tutoring, and is an example of a smart tutoring system, a specific type of knowledge-based application. Clancey showed that it was not enough simply to utilize MYCIN’s guidelines for instruction, however that he likewise needed to add rules for discussion management and trainee modeling. [50] XCON is significant because of the millions of dollars it conserved DEC, which triggered the professional system boom where most all major corporations in the US had professional systems groups, to catch corporate knowledge, preserve it, and automate it:

By 1988, DEC’s AI group had 40 specialist systems released, with more en route. DuPont had 100 in usage and 500 in development. Nearly every major U.S. corporation had its own Al group and was either using or investigating expert systems. [49]

Chess professional understanding was encoded in Deep Blue. In 1996, this permitted IBM’s Deep Blue, with the assistance of symbolic AI, to win in a game of chess versus the world champ at that time, Garry Kasparov. [52]

Architecture of knowledge-based and professional systems

A key element of the system architecture for all expert systems is the knowledge base, which shops truths and rules for problem-solving. [53] The simplest approach for a professional system knowledge base is just a collection or network of production guidelines. Production rules link symbols in a relationship similar to an If-Then declaration. The specialist system processes the rules to make reductions and to identify what additional info it needs, i.e. what questions to ask, utilizing human-readable symbols. For example, OPS5, CLIPS and their followers Jess and Drools operate in this fashion.

Expert systems can run in either a forward chaining – from evidence to conclusions – or backward chaining – from objectives to needed data and prerequisites – manner. Advanced knowledge-based systems, such as Soar can also perform meta-level thinking, that is reasoning about their own reasoning in regards to deciding how to resolve problems and keeping track of the success of problem-solving strategies.

Blackboard systems are a second type of knowledge-based or expert system architecture. They model a community of experts incrementally contributing, where they can, to solve a problem. The issue is represented in numerous levels of abstraction or alternate views. The experts (knowledge sources) volunteer their services whenever they acknowledge they can contribute. Potential analytical actions are represented on a program that is upgraded as the problem situation changes. A controller decides how useful each contribution is, and who should make the next analytical action. One example, the BB1 blackboard architecture [54] was originally influenced by research studies of how human beings prepare to perform numerous jobs in a trip. [55] An innovation of BB1 was to use the same blackboard design to solving its control problem, i.e., its controller performed meta-level reasoning with knowledge sources that monitored how well a plan or the problem-solving was continuing and could switch from one strategy to another as conditions – such as objectives or times – altered. BB1 has been used in multiple domains: construction website planning, smart tutoring systems, and real-time client monitoring.

The second AI winter season, 1988-1993

At the height of the AI boom, business such as Symbolics, LMI, and Texas Instruments were selling LISP devices particularly targeted to accelerate the development of AI applications and research. In addition, several expert system companies, such as Teknowledge and Inference Corporation, were selling skilled system shells, training, and consulting to corporations.

Unfortunately, the AI boom did not last and Kautz best describes the second AI winter season that followed:

Many factors can be provided for the arrival of the 2nd AI winter season. The hardware business stopped working when far more cost-efficient general Unix workstations from Sun together with great compilers for LISP and Prolog came onto the market. Many business releases of professional systems were terminated when they showed too expensive to keep. Medical expert systems never caught on for several factors: the trouble in keeping them approximately date; the difficulty for doctor to learn how to use a bewildering variety of different expert systems for various medical conditions; and possibly most crucially, the hesitation of medical professionals to trust a computer-made diagnosis over their gut impulse, even for specific domains where the professional systems might outshine a typical doctor. Venture capital money deserted AI practically over night. The world AI conference IJCAI hosted an enormous and luxurious exhibition and thousands of nonacademic participants in 1987 in Vancouver; the primary AI conference the following year, AAAI 1988 in St. Paul, was a little and strictly scholastic affair. [9]

Adding in more extensive structures, 1993-2011

Uncertain thinking

Both analytical techniques and extensions to reasoning were attempted.

One statistical technique, concealed Markov models, had currently been popularized in the 1980s for speech recognition work. [11] Subsequently, in 1988, Judea Pearl promoted making use of Bayesian Networks as a noise however efficient method of dealing with unpredictable thinking with his publication of the book Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. [56] and Bayesian techniques were used successfully in expert systems. [57] Even later on, in the 1990s, statistical relational knowing, a method that combines probability with sensible formulas, enabled likelihood to be combined with first-order logic, e.g., with either Markov Logic Networks or Probabilistic Soft Logic.

Other, non-probabilistic extensions to first-order reasoning to assistance were likewise attempted. For example, non-monotonic thinking could be utilized with fact upkeep systems. A fact maintenance system tracked assumptions and reasons for all inferences. It enabled inferences to be withdrawn when assumptions were learnt to be incorrect or a contradiction was derived. Explanations might be offered a reasoning by describing which rules were used to create it and then continuing through underlying inferences and rules all the way back to root presumptions. [58] Lofti Zadeh had presented a various kind of extension to manage the representation of vagueness. For example, in choosing how « heavy » or « tall » a man is, there is frequently no clear « yes » or « no » answer, and a predicate for heavy or tall would rather return values in between 0 and 1. Those worths represented to what degree the predicates held true. His fuzzy reasoning even more supplied a means for propagating mixes of these worths through sensible formulas. [59]

Machine knowing

Symbolic machine finding out techniques were investigated to attend to the understanding acquisition bottleneck. Among the earliest is Meta-DENDRAL. Meta-DENDRAL used a generate-and-test technique to create plausible guideline hypotheses to test against spectra. Domain and job understanding reduced the number of prospects tested to a workable size. Feigenbaum described Meta-DENDRAL as

… the conclusion of my dream of the early to mid-1960s relating to theory development. The conception was that you had an issue solver like DENDRAL that took some inputs and produced an output. In doing so, it utilized layers of understanding to steer and prune the search. That knowledge got in there since we spoke with people. But how did individuals get the knowledge? By looking at thousands of spectra. So we wanted a program that would look at countless spectra and infer the understanding of mass spectrometry that DENDRAL might utilize to fix private hypothesis formation problems. We did it. We were even able to publish new knowledge of mass spectrometry in the Journal of the American Chemical Society, giving credit just in a footnote that a program, Meta-DENDRAL, in fact did it. We were able to do something that had actually been a dream: to have a computer system program come up with a new and publishable piece of science. [51]

In contrast to the knowledge-intensive approach of Meta-DENDRAL, Ross Quinlan developed a domain-independent approach to statistical category, decision tree knowing, starting first with ID3 [60] and then later extending its capabilities to C4.5. [61] The decision trees produced are glass box, interpretable classifiers, with human-interpretable classification guidelines.

Advances were made in comprehending artificial intelligence theory, too. Tom Mitchell introduced variation space learning which explains learning as a search through a space of hypotheses, with upper, more general, and lower, more specific, boundaries encompassing all feasible hypotheses constant with the examples seen up until now. [62] More formally, Valiant introduced Probably Approximately Correct Learning (PAC Learning), a structure for the mathematical analysis of artificial intelligence. [63]

Symbolic machine learning encompassed more than learning by example. E.g., John Anderson offered a cognitive design of human learning where ability practice leads to a collection of rules from a declarative format to a procedural format with his ACT-R cognitive architecture. For example, a student may learn to apply « Supplementary angles are 2 angles whose steps sum 180 degrees » as numerous various procedural rules. E.g., one rule may say that if X and Y are supplemental and you understand X, then Y will be 180 – X. He called his method « knowledge collection ». ACT-R has actually been utilized successfully to model aspects of human cognition, such as discovering and retention. ACT-R is also used in smart tutoring systems, called cognitive tutors, to effectively teach geometry, computer programming, and algebra to school kids. [64]

Inductive reasoning programs was another technique to discovering that allowed reasoning programs to be manufactured from input-output examples. E.g., Ehud Shapiro’s MIS (Model Inference System) could manufacture Prolog programs from examples. [65] John R. Koza used genetic algorithms to program synthesis to create hereditary programming, which he used to manufacture LISP programs. Finally, Zohar Manna and Richard Waldinger provided a more general approach to program synthesis that manufactures a functional program in the course of proving its specifications to be correct. [66]

As an alternative to reasoning, Roger Schank introduced case-based reasoning (CBR). The CBR technique outlined in his book, Dynamic Memory, [67] focuses initially on remembering key problem-solving cases for future use and generalizing them where proper. When confronted with a brand-new problem, CBR retrieves the most similar previous case and adapts it to the specifics of the current problem. [68] Another option to logic, hereditary algorithms and hereditary programs are based upon an evolutionary design of knowing, where sets of guidelines are encoded into populations, the guidelines govern the behavior of individuals, and choice of the fittest prunes out sets of inappropriate rules over numerous generations. [69]

Symbolic artificial intelligence was applied to discovering concepts, guidelines, heuristics, and analytical. Approaches, besides those above, include:

1. Learning from direction or advice-i.e., taking human instruction, presented as recommendations, and determining how to operationalize it in specific circumstances. For instance, in a game of Hearts, discovering exactly how to play a hand to « prevent taking points. » [70] 2. Learning from exemplars-improving performance by accepting subject-matter specialist (SME) feedback throughout training. When analytical fails, querying the expert to either find out a brand-new prototype for analytical or to find out a new explanation regarding exactly why one exemplar is more pertinent than another. For instance, the program Protos found out to diagnose ringing in the ears cases by connecting with an audiologist. [71] 3. Learning by analogy-constructing problem solutions based on similar issues seen in the past, and then modifying their solutions to fit a brand-new situation or domain. [72] [73] 4. Apprentice learning systems-learning novel solutions to problems by observing human problem-solving. Domain knowledge explains why novel solutions are correct and how the solution can be generalized. LEAP found out how to create VLSI circuits by observing human designers. [74] 5. Learning by discovery-i.e., producing tasks to bring out experiments and after that discovering from the results. Doug Lenat’s Eurisko, for example, learned heuristics to beat human players at the Traveller role-playing game for two years in a row. [75] 6. Learning macro-operators-i.e., searching for useful macro-operators to be gained from series of fundamental analytical actions. Good macro-operators simplify problem-solving by allowing issues to be resolved at a more abstract level. [76]
Deep knowing and neuro-symbolic AI 2011-now

With the increase of deep knowing, the symbolic AI technique has actually been compared to deep knowing as complementary « … with parallels having been drawn often times by AI researchers between Kahneman’s research on human reasoning and choice making – shown in his book Thinking, Fast and Slow – and the so-called « AI systems 1 and 2″, which would in principle be modelled by deep learning and symbolic reasoning, respectively. » In this view, symbolic thinking is more apt for deliberative reasoning, planning, and description while deep knowing is more apt for quick pattern acknowledgment in perceptual applications with noisy information. [17] [18]

Neuro-symbolic AI: incorporating neural and symbolic methods

Neuro-symbolic AI efforts to incorporate neural and symbolic architectures in a way that addresses strengths and weaknesses of each, in a complementary fashion, in order to support robust AI capable of reasoning, learning, and cognitive modeling. As argued by Valiant [77] and many others, [78] the effective construction of rich computational cognitive models demands the mix of sound symbolic reasoning and efficient (maker) knowing models. Gary Marcus, likewise, argues that: « We can not construct abundant cognitive designs in an appropriate, automatic way without the triune of hybrid architecture, rich anticipation, and advanced methods for reasoning. », [79] and in specific: « To build a robust, knowledge-driven technique to AI we need to have the equipment of symbol-manipulation in our toolkit. Too much of beneficial knowledge is abstract to make do without tools that represent and control abstraction, and to date, the only equipment that we understand of that can manipulate such abstract understanding reliably is the device of symbol control.  » [80]

Henry Kautz, [19] Francesca Rossi, [81] and Bart Selman [82] have also argued for a synthesis. Their arguments are based upon a requirement to deal with the 2 kinds of thinking gone over in Daniel Kahneman’s book, Thinking, Fast and Slow. Kahneman describes human thinking as having 2 components, System 1 and System 2. System 1 is quick, automatic, instinctive and unconscious. System 2 is slower, detailed, and specific. System 1 is the kind used for pattern acknowledgment while System 2 is far better suited for planning, deduction, and deliberative thinking. In this view, deep learning finest models the very first sort of thinking while symbolic reasoning finest designs the 2nd kind and both are required.

Garcez and Lamb describe research in this location as being continuous for at least the past twenty years, [83] dating from their 2002 book on neurosymbolic learning systems. [84] A series of workshops on neuro-symbolic thinking has been held every year given that 2005, see http://www.neural-symbolic.org/ for details.

In their 2015 paper, Neural-Symbolic Learning and Reasoning: Contributions and Challenges, Garcez et al. argue that:

The integration of the symbolic and connectionist paradigms of AI has been pursued by a fairly small research community over the last 20 years and has actually yielded a number of significant outcomes. Over the last years, neural symbolic systems have been shown efficient in conquering the so-called propositional fixation of neural networks, as McCarthy (1988) put it in reaction to Smolensky (1988 ); see likewise (Hinton, 1990). Neural networks were shown efficient in representing modal and temporal reasonings (d’Avila Garcez and Lamb, 2006) and pieces of first-order logic (Bader, Hitzler, Hölldobler, 2008; d’Avila Garcez, Lamb, Gabbay, 2009). Further, neural-symbolic systems have been used to a variety of problems in the areas of bioinformatics, control engineering, software confirmation and adaptation, visual intelligence, ontology knowing, and computer system video games. [78]

Approaches for integration are differed. Henry Kautz’s taxonomy of neuro-symbolic architectures, together with some examples, follows:

– Symbolic Neural symbolic-is the current method of many neural models in natural language processing, where words or subword tokens are both the ultimate input and output of big language designs. Examples consist of BERT, RoBERTa, and GPT-3.
– Symbolic [Neural] -is exhibited by AlphaGo, where symbolic techniques are used to call neural methods. In this case the symbolic technique is Monte Carlo tree search and the neural strategies find out how to examine video game positions.
– Neural|Symbolic-uses a neural architecture to analyze perceptual data as symbols and relationships that are then reasoned about symbolically.
– Neural: Symbolic → Neural-relies on symbolic thinking to create or identify training information that is subsequently found out by a deep learning design, e.g., to train a neural model for symbolic calculation by utilizing a Macsyma-like symbolic mathematics system to develop or identify examples.
– Neural _ Symbolic -utilizes a neural internet that is produced from symbolic rules. An example is the Neural Theorem Prover, [85] which constructs a neural network from an AND-OR proof tree generated from knowledge base guidelines and terms. Logic Tensor Networks [86] also fall into this classification.
– Neural [Symbolic] -allows a neural model to directly call a symbolic thinking engine, e.g., to perform an action or examine a state.

Many essential research concerns stay, such as:

– What is the very best method to integrate neural and symbolic architectures? [87]- How should symbolic structures be represented within neural networks and drawn out from them?
– How should common-sense understanding be learned and reasoned about?
– How can abstract understanding that is difficult to encode realistically be dealt with?

Techniques and contributions

This area offers a summary of strategies and contributions in an overall context causing lots of other, more in-depth short articles in Wikipedia. Sections on Machine Learning and Uncertain Reasoning are covered earlier in the history section.

AI programming languages

The key AI programs language in the US during the last symbolic AI boom period was LISP. LISP is the second earliest programs language after FORTRAN and was produced in 1958 by John McCarthy. LISP supplied the very first read-eval-print loop to support fast program development. Compiled functions could be easily blended with interpreted functions. Program tracing, stepping, and breakpoints were likewise provided, in addition to the ability to change worths or functions and continue from breakpoints or mistakes. It had the very first self-hosting compiler, suggesting that the compiler itself was initially composed in LISP and then ran interpretively to put together the compiler code.

Other key developments pioneered by LISP that have infected other programming languages consist of:

Garbage collection
Dynamic typing
Higher-order functions
Recursion
Conditionals

Programs were themselves data structures that other programs could run on, permitting the easy meaning of higher-level languages.

In contrast to the US, in Europe the essential AI programs language throughout that same duration was Prolog. Prolog supplied an integrated store of truths and stipulations that might be queried by a read-eval-print loop. The store might serve as a knowledge base and the clauses could function as rules or a limited kind of reasoning. As a subset of first-order logic Prolog was based on Horn clauses with a closed-world assumption-any facts not known were thought about false-and a special name assumption for primitive terms-e.g., the identifier barack_obama was considered to describe exactly one item. Backtracking and marriage are integrated to Prolog.

Alain Colmerauer and Philippe Roussel are credited as the developers of Prolog. Prolog is a kind of reasoning programs, which was created by Robert Kowalski. Its history was also affected by Carl Hewitt’s PLANNER, an assertional database with pattern-directed invocation of methods. For more information see the area on the origins of Prolog in the PLANNER post.

Prolog is also a kind of declarative programming. The logic clauses that explain programs are directly translated to run the programs specified. No explicit series of actions is needed, as is the case with important shows languages.

Japan championed Prolog for its Fifth Generation Project, planning to develop special hardware for high performance. Similarly, LISP devices were developed to run LISP, however as the 2nd AI boom turned to bust these companies could not take on new workstations that could now run LISP or Prolog natively at comparable speeds. See the history area for more detail.

Smalltalk was another prominent AI programming language. For instance, it introduced metaclasses and, in addition to Flavors and CommonLoops, affected the Common Lisp Object System, or (CLOS), that is now part of Common Lisp, the current standard Lisp dialect. CLOS is a Lisp-based object-oriented system that allows several inheritance, in addition to incremental extensions to both classes and metaclasses, therefore supplying a run-time meta-object protocol. [88]

For other AI programming languages see this list of programs languages for synthetic intelligence. Currently, Python, a multi-paradigm shows language, is the most popular programming language, partly due to its extensive plan library that supports information science, natural language processing, and deep learning. Python includes a read-eval-print loop, functional elements such as higher-order functions, and object-oriented programming that consists of metaclasses.

Search

Search emerges in lots of kinds of problem fixing, consisting of preparation, restriction complete satisfaction, and playing video games such as checkers, chess, and go. The best understood AI-search tree search algorithms are breadth-first search, depth-first search, A *, and Monte Carlo Search. Key search algorithms for Boolean satisfiability are WalkSAT, conflict-driven clause learning, and the DPLL algorithm. For adversarial search when playing games, alpha-beta pruning, branch and bound, and minimax were early contributions.

Knowledge representation and reasoning

Multiple different techniques to represent knowledge and after that factor with those representations have been examined. Below is a fast overview of methods to knowledge representation and automated thinking.

Knowledge representation

Semantic networks, conceptual graphs, frames, and reasoning are all approaches to modeling knowledge such as domain knowledge, problem-solving knowledge, and the semantic significance of language. Ontologies model essential principles and their relationships in a domain. Example ontologies are YAGO, WordNet, and DOLCE. DOLCE is an example of an upper ontology that can be used for any domain while WordNet is a lexical resource that can likewise be seen as an ontology. YAGO incorporates WordNet as part of its ontology, to align realities extracted from Wikipedia with WordNet synsets. The Disease Ontology is an example of a medical ontology presently being utilized.

Description reasoning is a reasoning for automated category of ontologies and for detecting inconsistent classification information. OWL is a language used to represent ontologies with description logic. Protégé is an ontology editor that can read in OWL ontologies and after that inspect consistency with deductive classifiers such as such as HermiT. [89]

First-order logic is more basic than description logic. The automated theorem provers discussed listed below can show theorems in first-order reasoning. Horn stipulation reasoning is more limited than first-order reasoning and is used in reasoning shows languages such as Prolog. Extensions to first-order reasoning consist of temporal logic, to handle time; epistemic reasoning, to reason about agent understanding; modal logic, to handle possibility and requirement; and probabilistic reasonings to deal with reasoning and likelihood together.

Automatic theorem showing

Examples of automated theorem provers for first-order logic are:

Prover9.
ACL2.
Vampire.

Prover9 can be used in combination with the Mace4 model checker. ACL2 is a theorem prover that can manage proofs by induction and is a descendant of the Boyer-Moore Theorem Prover, also referred to as Nqthm.

Reasoning in knowledge-based systems

Knowledge-based systems have a specific understanding base, typically of rules, to boost reusability throughout domains by separating procedural code and domain knowledge. A separate inference engine processes guidelines and includes, deletes, or customizes an understanding shop.

Forward chaining inference engines are the most typical, and are seen in CLIPS and OPS5. Backward chaining takes place in Prolog, where a more minimal sensible representation is used, Horn Clauses. Pattern-matching, specifically marriage, is used in Prolog.

A more flexible kind of problem-solving takes place when thinking about what to do next takes place, rather than just selecting one of the available actions. This sort of meta-level reasoning is used in Soar and in the BB1 chalkboard architecture.

Cognitive architectures such as ACT-R might have additional abilities, such as the ability to put together regularly utilized understanding into higher-level portions.

Commonsense thinking

Marvin Minsky initially proposed frames as a way of translating common visual scenarios, such as a workplace, and Roger Schank extended this idea to scripts for typical routines, such as eating in restaurants. Cyc has attempted to capture useful common-sense knowledge and has « micro-theories » to deal with particular kinds of domain-specific thinking.

Qualitative simulation, such as Benjamin Kuipers’s QSIM, [90] approximates human thinking about naive physics, such as what occurs when we heat up a liquid in a pot on the range. We expect it to heat and perhaps boil over, although we may not understand its temperature level, its boiling point, or other information, such as climatic pressure.

Similarly, Allen’s temporal interval algebra is a simplification of reasoning about time and Region Connection Calculus is a simplification of thinking about spatial relationships. Both can be solved with restriction solvers.

Constraints and constraint-based thinking

Constraint solvers carry out a more limited type of inference than first-order reasoning. They can simplify sets of spatiotemporal constraints, such as those for RCC or Temporal Algebra, along with resolving other sort of puzzle issues, such as Wordle, Sudoku, cryptarithmetic problems, and so on. Constraint reasoning shows can be used to solve scheduling problems, for instance with restriction dealing with rules (CHR).

Automated preparation

The General Problem Solver (GPS) cast planning as problem-solving used means-ends analysis to develop strategies. STRIPS took a different method, viewing planning as theorem proving. Graphplan takes a least-commitment technique to preparation, instead of sequentially picking actions from a preliminary state, working forwards, or an objective state if working backwards. Satplan is an approach to planning where a preparation issue is minimized to a Boolean satisfiability problem.

Natural language processing

Natural language processing concentrates on treating language as information to perform jobs such as recognizing topics without always understanding the intended significance. Natural language understanding, on the other hand, constructs a significance representation and utilizes that for additional processing, such as addressing questions.

Parsing, tokenizing, spelling correction, part-of-speech tagging, noun and verb phrase chunking are all elements of natural language processing long handled by symbolic AI, however given that enhanced by deep learning techniques. In symbolic AI, discourse representation theory and first-order reasoning have actually been utilized to represent sentence meanings. Latent semantic analysis (LSA) and explicit semantic analysis also supplied vector representations of files. In the latter case, vector components are interpretable as ideas called by Wikipedia articles.

New deep knowing techniques based on Transformer designs have actually now eclipsed these earlier symbolic AI approaches and achieved advanced performance in natural language processing. However, Transformer models are opaque and do not yet produce human-interpretable semantic representations for sentences and files. Instead, they produce task-specific vectors where the significance of the vector parts is nontransparent.

Agents and multi-agent systems

Agents are self-governing systems embedded in an environment they perceive and act on in some sense. Russell and Norvig’s standard textbook on artificial intelligence is organized to reflect representative architectures of increasing elegance. [91] The sophistication of agents varies from simple reactive representatives, to those with a model of the world and automated planning abilities, perhaps a BDI agent, i.e., one with beliefs, desires, and objectives – or additionally a support finding out design discovered in time to choose actions – approximately a combination of alternative architectures, such as a neuro-symbolic architecture [87] that includes deep knowing for understanding. [92]

On the other hand, a multi-agent system consists of several representatives that communicate amongst themselves with some inter-agent communication language such as Knowledge Query and Manipulation Language (KQML). The agents need not all have the exact same internal architecture. Advantages of multi-agent systems include the ability to divide work among the agents and to increase fault tolerance when agents are lost. Research issues include how representatives reach agreement, dispersed issue fixing, multi-agent learning, multi-agent preparation, and dispersed constraint optimization.

Controversies developed from early in symbolic AI, both within the field-e.g., in between logicists (the pro-logic « neats ») and non-logicists (the anti-logic « scruffies »)- and between those who welcomed AI however declined symbolic approaches-primarily connectionists-and those outside the field. Critiques from exterior of the field were primarily from thinkers, on intellectual grounds, however likewise from funding agencies, specifically throughout the 2 AI winters.

The Frame Problem: knowledge representation challenges for first-order logic

Limitations were found in utilizing simple first-order reasoning to reason about dynamic domains. Problems were discovered both with regards to mentioning the prerequisites for an action to be successful and in providing axioms for what did not alter after an action was carried out.

McCarthy and Hayes introduced the Frame Problem in 1969 in the paper, « Some Philosophical Problems from the Standpoint of Artificial Intelligence. » [93] A basic example happens in « showing that a person person might enter into conversation with another », as an axiom asserting « if an individual has a telephone he still has it after searching for a number in the telephone book » would be needed for the deduction to succeed. Similar axioms would be needed for other domain actions to define what did not change.

A comparable problem, called the Qualification Problem, occurs in trying to enumerate the preconditions for an action to be successful. A limitless variety of pathological conditions can be thought of, e.g., a banana in a tailpipe might prevent an automobile from operating correctly.

McCarthy’s technique to repair the frame problem was circumscription, a sort of non-monotonic logic where deductions could be made from actions that require only define what would change while not having to clearly define whatever that would not change. Other non-monotonic logics supplied reality upkeep systems that revised beliefs resulting in contradictions.

Other ways of handling more open-ended domains included probabilistic thinking systems and machine learning to find out new concepts and guidelines. McCarthy’s Advice Taker can be considered as an inspiration here, as it could include brand-new knowledge supplied by a human in the kind of assertions or guidelines. For instance, speculative symbolic machine discovering systems explored the ability to take high-level natural language recommendations and to interpret it into domain-specific actionable rules.

Similar to the issues in managing vibrant domains, common-sense thinking is also challenging to capture in official thinking. Examples of common-sense reasoning include implicit reasoning about how people think or general understanding of everyday events, objects, and living creatures. This type of knowledge is considered approved and not considered as noteworthy. Common-sense thinking is an open area of research study and challenging both for symbolic systems (e.g., Cyc has tried to catch essential parts of this knowledge over more than a decade) and neural systems (e.g., self-driving cars that do not know not to drive into cones or not to strike pedestrians strolling a bicycle).

McCarthy viewed his Advice Taker as having common-sense, but his meaning of common-sense was various than the one above. [94] He specified a program as having good sense « if it automatically deduces for itself a sufficiently wide class of immediate repercussions of anything it is informed and what it already knows. « 

Connectionist AI: philosophical obstacles and sociological disputes

Connectionist methods consist of earlier work on neural networks, [95] such as perceptrons; work in the mid to late 80s, such as Danny Hillis’s Connection Machine and Yann LeCun’s advances in convolutional neural networks; to today’s more innovative methods, such as Transformers, GANs, and other work in deep learning.

Three philosophical positions [96] have actually been outlined amongst connectionists:

1. Implementationism-where connectionist architectures implement the capabilities for symbolic processing,
2. Radical connectionism-where symbolic processing is rejected completely, and connectionist architectures underlie intelligence and are fully adequate to describe it,
3. Moderate connectionism-where symbolic processing and connectionist architectures are seen as complementary and both are needed for intelligence

Olazaran, in his sociological history of the debates within the neural network neighborhood, explained the moderate connectionism view as basically suitable with existing research study in neuro-symbolic hybrids:

The third and last position I wish to take a look at here is what I call the moderate connectionist view, a more eclectic view of the current dispute in between connectionism and symbolic AI. One of the researchers who has elaborated this position most explicitly is Andy Clark, a theorist from the School of Cognitive and Computing Sciences of the University of Sussex (Brighton, England). Clark protected hybrid (partially symbolic, partly connectionist) systems. He claimed that (at least) two kinds of theories are required in order to study and design cognition. On the one hand, for some information-processing tasks (such as pattern recognition) connectionism has benefits over symbolic designs. But on the other hand, for other cognitive procedures (such as serial, deductive thinking, and generative symbol control procedures) the symbolic paradigm uses adequate designs, and not just « approximations » (contrary to what radical connectionists would declare). [97]

Gary Marcus has actually declared that the animus in the deep learning community versus symbolic approaches now might be more sociological than philosophical:

To believe that we can just desert symbol-manipulation is to suspend shock.

And yet, for the most part, that’s how most current AI earnings. Hinton and numerous others have actually striven to get rid of symbols altogether. The deep learning hope-seemingly grounded not so much in science, however in a sort of historic grudge-is that intelligent habits will emerge simply from the confluence of enormous information and deep learning. Where classical computers and software application fix tasks by specifying sets of symbol-manipulating rules devoted to particular tasks, such as modifying a line in a word processor or carrying out a computation in a spreadsheet, neural networks normally try to resolve tasks by analytical approximation and gaining from examples.

According to Marcus, Geoffrey Hinton and his colleagues have actually been emphatically « anti-symbolic »:

When deep learning reemerged in 2012, it was with a type of take-no-prisoners mindset that has actually identified most of the last decade. By 2015, his hostility toward all things signs had completely crystallized. He lectured at an AI workshop at Stanford comparing signs to aether, among science’s greatest mistakes.

Since then, his anti-symbolic project has only increased in intensity. In 2016, Yann LeCun, Bengio, and Hinton composed a manifesto for deep knowing in among science’s most important journals, Nature. It closed with a direct attack on sign adjustment, calling not for reconciliation but for straight-out replacement. Later, Hinton told an event of European Union leaders that investing any more cash in symbol-manipulating approaches was « a substantial error, » likening it to purchasing internal combustion engines in the age of electrical cars. [98]

Part of these disagreements might be due to unclear terminology:

Turing award winner Judea Pearl provides a critique of artificial intelligence which, regrettably, conflates the terms maker learning and deep knowing. Similarly, when Geoffrey Hinton refers to symbolic AI, the connotation of the term tends to be that of expert systems dispossessed of any capability to find out. Using the terms is in requirement of clarification. Artificial intelligence is not confined to association rule mining, c.f. the body of work on symbolic ML and relational learning (the distinctions to deep learning being the choice of representation, localist rational instead of dispersed, and the non-use of gradient-based learning algorithms). Equally, symbolic AI is not almost production rules composed by hand. A proper meaning of AI issues knowledge representation and reasoning, autonomous multi-agent systems, preparation and argumentation, as well as learning. [99]

Situated robotics: the world as a model

Another critique of symbolic AI is the embodied cognition approach:

The embodied cognition approach declares that it makes no sense to think about the brain individually: cognition occurs within a body, which is embedded in an environment. We need to study the system as a whole; the brain’s working exploits regularities in its environment, including the rest of its body. Under the embodied cognition method, robotics, vision, and other sensors become main, not peripheral. [100]

Rodney Brooks created behavior-based robotics, one approach to embodied cognition. Nouvelle AI, another name for this method, is deemed an alternative to both symbolic AI and connectionist AI. His technique turned down representations, either symbolic or dispersed, as not only unnecessary, however as damaging. Instead, he produced the subsumption architecture, a layered architecture for embodied agents. Each layer attains a different function and should operate in the real life. For example, the very first robotic he explains in Intelligence Without Representation, has 3 layers. The bottom layer interprets finder sensors to avoid things. The middle layer triggers the robot to roam around when there are no barriers. The top layer triggers the robotic to go to more far-off locations for more exploration. Each layer can momentarily prevent or suppress a lower-level layer. He slammed AI researchers for defining AI problems for their systems, when: « There is no clean division between understanding (abstraction) and reasoning in the real life. » [101] He called his robots « Creatures » and each layer was « made up of a fixed-topology network of simple finite state makers. » [102] In the Nouvelle AI technique, « First, it is extremely essential to evaluate the Creatures we construct in the genuine world; i.e., in the exact same world that we humans inhabit. It is devastating to fall under the temptation of checking them in a simplified world first, even with the very best objectives of later transferring activity to an unsimplified world. » [103] His emphasis on real-world testing was in contrast to « Early work in AI focused on video games, geometrical problems, symbolic algebra, theorem proving, and other formal systems » [104] and making use of the blocks world in symbolic AI systems such as SHRDLU.

Current views

Each approach-symbolic, connectionist, and behavior-based-has benefits, but has actually been slammed by the other techniques. Symbolic AI has been slammed as disembodied, accountable to the credentials issue, and bad in dealing with the perceptual problems where deep discovering excels. In turn, connectionist AI has been criticized as improperly matched for deliberative detailed issue fixing, incorporating understanding, and managing preparation. Finally, Nouvelle AI masters reactive and real-world robotics domains however has been slammed for difficulties in incorporating knowing and understanding.

Hybrid AIs incorporating several of these approaches are currently considered as the course forward. [19] [81] [82] Russell and Norvig conclude that:

Overall, Dreyfus saw locations where AI did not have complete answers and said that Al is for that reason impossible; we now see much of these very same locations undergoing continued research and advancement resulting in increased capability, not impossibility. [100]

Expert system.
Automated planning and scheduling
Automated theorem proving
Belief modification
Case-based thinking
Cognitive architecture
Cognitive science
Connectionism
Constraint programs
Deep knowing
First-order reasoning
GOFAI
History of expert system
Inductive logic programming
Knowledge-based systems
Knowledge representation and thinking
Logic shows
Machine learning
Model checking
Model-based reasoning
Multi-agent system
Natural language processing
Neuro-symbolic AI
Ontology
Philosophy of expert system
Physical sign systems hypothesis
Semantic Web
Sequential pattern mining
Statistical relational learning
Symbolic mathematics
YAGO ontology
WordNet

Notes

^ McCarthy as soon as stated: « This is AI, so we don’t care if it’s mentally real ». [4] McCarthy reiterated his position in 2006 at the AI@50 conference where he said « Expert system is not, by definition, simulation of human intelligence ». [28] Pamela McCorduck composes that there are « 2 major branches of expert system: one focused on producing intelligent behavior regardless of how it was accomplished, and the other targeted at modeling intelligent processes found in nature, particularly human ones. », [29] Stuart Russell and Peter Norvig composed « Aeronautical engineering texts do not define the goal of their field as making ‘makers that fly so exactly like pigeons that they can deceive even other pigeons.' » [30] Citations

^ Garnelo, Marta; Shanahan, Murray (October 2019). « Reconciling deep knowing with symbolic expert system: representing objects and relations ». Current Opinion in Behavioral Sciences. 29: 17-23. doi:10.1016/ j.cobeha.2018.12.010. hdl:10044/ 1/67796.
^ Thomason, Richmond (February 27, 2024). « Logic-Based Expert System ». In Zalta, Edward N. (ed.). Stanford Encyclopedia of Philosophy.
^ Garnelo, Marta; Shanahan, Murray (2019-10-01). « Reconciling deep learning with symbolic synthetic intelligence: representing items and relations ». Current Opinion in Behavioral Sciences. 29: 17-23. doi:10.1016/ j.cobeha.2018.12.010. hdl:10044/ 1/67796. S2CID 72336067.
^ a b Kolata 1982.
^ Kautz 2022, pp. 107-109.
^ a b Russell & Norvig 2021, p. 19.
^ a b Russell & Norvig 2021, pp. 22-23.
^ a b Kautz 2022, pp. 109-110.
^ a b c Kautz 2022, p. 110.
^ Kautz 2022, pp. 110-111.
^ a b Russell & Norvig 2021, p. 25.
^ Kautz 2022, p. 111.
^ Kautz 2020, pp. 110-111.
^ Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J. (1986 ). « Learning representations by back-propagating errors ». Nature. 323 (6088 ): 533-536. Bibcode:1986 Natur.323..533 R. doi:10.1038/ 323533a0. ISSN 1476-4687. S2CID 205001834.
^ LeCun, Y.; Boser, B.; Denker, I.; Henderson, D.; Howard, R.; Hubbard, W.; Tackel, L. (1989 ). « Backpropagation Applied to Handwritten Postal Code Recognition ». Neural Computation. 1 (4 ): 541-551. doi:10.1162/ neco.1989.1.4.541. S2CID 41312633.
^ a b Marcus & Davis 2019.
^ a b Rossi, Francesca. « Thinking Fast and Slow in AI ». AAAI. Retrieved 5 July 2022.
^ a b Selman, Bart. « AAAI Presidential Address: The State of AI ». AAAI. Retrieved 5 July 2022.
^ a b c Kautz 2020.
^ Kautz 2022, p. 106.
^ Newell & Simon 1972.
^ & McCorduck 2004, pp. 139-179, 245-250, 322-323 (EPAM).
^ Crevier 1993, pp. 145-149.
^ McCorduck 2004, pp. 450-451.
^ Crevier 1993, pp. 258-263.
^ a b Kautz 2022, p. 108.
^ Russell & Norvig 2021, p. 9 (logicist AI), p. 19 (McCarthy’s work).
^ Maker 2006.
^ McCorduck 2004, pp. 100-101.
^ Russell & Norvig 2021, p. 2.
^ McCorduck 2004, pp. 251-259.
^ Crevier 1993, pp. 193-196.
^ Howe 1994.
^ McCorduck 2004, pp. 259-305.
^ Crevier 1993, pp. 83-102, 163-176.
^ McCorduck 2004, pp. 421-424, 486-489.
^ Crevier 1993, p. 168.
^ McCorduck 2004, p. 489.
^ Crevier 1993, pp. 239-243.
^ Russell & Norvig 2021, p. 316, 340.
^ Kautz 2022, p. 109.
^ Russell & Norvig 2021, p. 22.
^ McCorduck 2004, pp. 266-276, 298-300, 314, 421.
^ Shustek, Len (June 2010). « An interview with Ed Feigenbaum ». Communications of the ACM. 53 (6 ): 41-45. doi:10.1145/ 1743546.1743564. ISSN 0001-0782. S2CID 10239007. Retrieved 2022-07-14.
^ Lenat, Douglas B; Feigenbaum, Edward A (1988 ). « On the limits of knowledge ». Proceedings of the International Workshop on Artificial Intelligence for Industrial Applications: 291-300. doi:10.1109/ AIIA.1988.13308. S2CID 11778085.
^ Russell & Norvig 2021, pp. 22-24.
^ McCorduck 2004, pp. 327-335, 434-435.
^ Crevier 1993, pp. 145-62, 197-203.
^ a b Russell & Norvig 2021, p. 23.
^ a b Clancey 1987.
^ a b Shustek, Len (2010 ). « An interview with Ed Feigenbaum ». Communications of the ACM. 53 (6 ): 41-45. doi:10.1145/ 1743546.1743564. ISSN 0001-0782. S2CID 10239007. Retrieved 2022-08-05.
^ « The fascination with AI: what is expert system? ». IONOS Digitalguide. Retrieved 2021-12-02.
^ Hayes-Roth, Murray & Adelman 2015.
^ Hayes-Roth, Barbara (1985 ). « A blackboard architecture for control ». Expert system. 26 (3 ): 251-321. doi:10.1016/ 0004-3702( 85 )90063-3.
^ Hayes-Roth, Barbara (1980 ). Human Planning Processes. RAND.
^ Pearl 1988.
^ Spiegelhalter et al. 1993.
^ Russell & Norvig 2021, pp. 335-337.
^ Russell & Norvig 2021, p. 459.
^ Quinlan, J. Ross. « Chapter 15: Learning Efficient Classification Procedures and their Application to Chess End Games ». In Michalski, Carbonell & Mitchell (1983 ).
^ Quinlan, J. Ross (1992-10-15). C4.5: Programs for Machine Learning (1st ed.). San Mateo, Calif: Morgan Kaufmann. ISBN 978-1-55860-238-0.
^ Mitchell, Tom M.; Utgoff, Paul E.; Banerji, Ranan. « Chapter 6: Learning by Experimentation: Acquiring and Refining Problem-Solving Heuristics ». In Michalski, Carbonell & Mitchell (1983 ).
^ Valiant, L. G. (1984-11-05). « A theory of the learnable ». Communications of the ACM. 27 (11 ): 1134-1142. doi:10.1145/ 1968.1972. ISSN 0001-0782. S2CID 12837541.
^ Koedinger, K. R.; Anderson, J. R.; Hadley, W. H.; Mark, M. A.; others (1997 ). « Intelligent tutoring goes to school in the huge city ». International Journal of Expert System in Education (IJAIED). 8: 30-43. Retrieved 2012-08-18.
^ Shapiro, Ehud Y (1981 ). « The Model Inference System ». Proceedings of the 7th worldwide joint conference on Expert system. IJCAI. Vol. 2. p. 1064.
^ Manna, Zohar; Waldinger, Richard (1980-01-01). « A Deductive Approach to Program Synthesis ». ACM Trans. Program. Lang. Syst. 2 (1 ): 90-121. doi:10.1145/ 357084.357090. S2CID 14770735.
^ Schank, Roger C. (1983-01-28). Dynamic Memory: A Theory of Reminding and Learning in Computers and People. Cambridge Cambridgeshire: New York: Cambridge University Press. ISBN 978-0-521-27029-8.
^ Hammond, Kristian J. (1989-04-11). Case-Based Planning: Viewing Planning as a Memory Task. Boston: Academic Press. ISBN 978-0-12-322060-8.
^ Koza, John R. (1992-12-11). Genetic Programming: On the Programming of Computers by Means of Natural Selection (1st ed.). Cambridge, Mass: A Bradford Book. ISBN 978-0-262-11170-6.
^ Mostow, David Jack. « Chapter 12: Machine Transformation of Advice into a Heuristic Search Procedure ». In Michalski, Carbonell & Mitchell (1983 ).
^ Bareiss, Ray; Porter, Bruce; Wier, Craig. « Chapter 4: Protos: An Exemplar-Based Learning Apprentice ». In Michalski, Carbonell & Mitchell (1986 ), pp. 112-139.
^ Carbonell, Jaime. « Chapter 5: Learning by Analogy: Formulating and Generalizing Plans from Past Experience ». In Michalski, Carbonell & Mitchell (1983 ), pp. 137-162.
^ Carbonell, Jaime. « Chapter 14: Derivational Analogy: A Theory of Reconstructive Problem Solving and Expertise Acquisition ». In Michalski, Carbonell & Mitchell (1986 ), pp. 371-392.
^ Mitchell, Tom; Mabadevan, Sridbar; Steinberg, Louis. « Chapter 10: LEAP: A Learning Apprentice for VLSI Design ». In Kodratoff & Michalski (1990 ), pp. 271-289.
^ Lenat, Douglas. « Chapter 9: The Role of Heuristics in Learning by Discovery: Three Case Studies ». In Michalski, Carbonell & Mitchell (1983 ), pp. 243-306.
^ Korf, Richard E. (1985 ). Learning to Solve Problems by Searching for Macro-Operators. Research Notes in Expert System. Pitman Publishing. ISBN 0-273-08690-1.
^ Valiant 2008.
^ a b Garcez et al. 2015.
^ Marcus 2020, p. 44.
^ Marcus 2020, p. 17.
^ a b Rossi 2022.
^ a b Selman 2022.
^ Garcez & Lamb 2020, p. 2.
^ Garcez et al. 2002.
^ Rocktäschel, Tim; Riedel, Sebastian (2016 ). « Learning Knowledge Base Inference with Neural Theorem Provers ». Proceedings of the fifth Workshop on Automated Knowledge Base Construction. San Diego, CA: Association for Computational Linguistics. pp. 45-50. doi:10.18653/ v1/W16 -1309. Retrieved 2022-08-06.
^ Serafini, Luciano; Garcez, Artur d’Avila (2016 ), Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge, arXiv:1606.04422.
^ a b Garcez, Artur d’Avila; Lamb, Luis C.; Gabbay, Dov M. (2009 ). Neural-Symbolic Cognitive Reasoning (1st ed.). Berlin-Heidelberg: Springer. Bibcode:2009 nscr.book … D. doi:10.1007/ 978-3-540-73246-4. ISBN 978-3-540-73245-7. S2CID 14002173.
^ Kiczales, Gregor; Rivieres, Jim des; Bobrow, Daniel G. (1991-07-30). The Art of the Metaobject Protocol (1st ed.). Cambridge, Mass: The MIT Press. ISBN 978-0-262-61074-2.
^ Motik, Boris; Shearer, Rob; Horrocks, Ian (2009-10-28). « Hypertableau Reasoning for Description Logics ». Journal of Expert System Research. 36: 165-228. arXiv:1401.3485. doi:10.1613/ jair.2811. ISSN 1076-9757. S2CID 190609.
^ Kuipers, Benjamin (1994 ). Qualitative Reasoning: Modeling and Simulation with Incomplete Knowledge. MIT Press. ISBN 978-0-262-51540-5.
^ Russell & Norvig 2021.
^ Leo de Penning, Artur S. d’Avila Garcez, Luís C. Lamb, John-Jules Ch. Meyer: « A Neural-Symbolic Cognitive Agent for Online Learning and Reasoning. » IJCAI 2011: 1653-1658.
^ McCarthy & Hayes 1969.
^ McCarthy 1959.
^ Nilsson 1998, p. 7.
^ Olazaran 1993, pp. 411-416.
^ Olazaran 1993, pp. 415-416.
^ Marcus 2020, p. 20.
^ Garcez & Lamb 2020, p. 8.
^ a b Russell & Norvig 2021, p. 982.
^ Brooks 1991, p. 143.
^ Brooks 1991, p. 151.
^ Brooks 1991, p. 150.
^ Brooks 1991, p. 142.
References

Brooks, Rodney A. (1991 ). « Intelligence without representation ». Expert system. 47 (1 ): 139-159. doi:10.1016/ 0004-3702( 91 )90053-M. ISSN 0004-3702. S2CID 207507849. Retrieved 2022-09-13.
Clancey, William (1987 ). Knowledge-Based Tutoring: The GUIDON Program (MIT Press Series in Artificial Intelligence) (Hardcover ed.).
Crevier, Daniel (1993 ). AI: The Tumultuous Search for Artificial Intelligence. New York City, NY: BasicBooks. ISBN 0-465-02997-3.
Dreyfus, Hubert L (1981 ). « From micro-worlds to understanding representation: AI at an impasse » (PDF). Mind Design. MIT Press, Cambridge, MA: 161-204.
Garcez, Artur S. d’Avila; Broda, Krysia; Gabbay, Dov M.; Gabbay, Augustus de Morgan Professor of Logic Dov M. (2002 ). Neural-Symbolic Learning Systems: Foundations and Applications. Springer Science & Business Media. ISBN 978-1-85233-512-0.
Garcez, Artur; Besold, Tarek; De Raedt, Luc; Földiák, Peter; Hitzler, Pascal; Icard, Thomas; Kühnberger, Kai-Uwe; Lamb, Luís; Miikkulainen, Risto; Silver, Daniel (2015 ). Neural-Symbolic Learning and Reasoning: Contributions and Challenges. AAI Spring Symposium – Knowledge Representation and Reasoning: Integrating Symbolic and Neural Approaches. Stanford, CA: AAAI Press. doi:10.13140/ 2.1.1779.4243.
Garcez, Artur d’Avila; Gori, Marco; Lamb, Luis C.; Serafini, Luciano; Spranger, Michael; Tran, Son N. (2019 ), Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning, arXiv:1905.06088.
Garcez, Artur d’Avila; Lamb, Luis C. (2020 ), Neurosymbolic AI: The 3rd Wave, arXiv:2012.05876.
Haugeland, John (1985 ), Artificial Intelligence: The Very Idea, Cambridge, Mass: MIT Press, ISBN 0-262-08153-9.
Hayes-Roth, Frederick; Murray, William; Adelman, Leonard (2015 ). « Expert systems ». AccessScience. doi:10.1036/ 1097-8542.248550.
Honavar, Vasant; Uhr, Leonard (1994 ). Symbolic Artificial Intelligence, Connectionist Networks & Beyond (Technical report). Iowa State University Digital Repository, Computer Science Technical Reports. 76. p. 6.
Honavar, Vasant (1995 ). Symbolic Expert System and Numeric Artificial Neural Networks: Towards a Resolution of the Dichotomy. The Springer International Series In Engineering and Computer Science. Springer US. pp. 351-388. doi:10.1007/ 978-0-585-29599-2_11.
Howe, J. (November 1994). « Artificial Intelligence at Edinburgh University: a Point of view ». Archived from the original on 15 May 2007. Retrieved 30 August 2007.
Kautz, Henry (2020-02-11). The Third AI Summer, Henry Kautz, AAAI 2020 Robert S. Engelmore Memorial Award Lecture. Retrieved 2022-07-06.
Kautz, Henry (2022 ). « The Third AI Summer: AAAI Robert S. Engelmore Memorial Lecture ». AI Magazine. 43 (1 ): 93-104. doi:10.1609/ aimag.v43i1.19122. ISSN 2371-9621. S2CID 248213051. Retrieved 2022-07-12.
Kodratoff, Yves; Michalski, Ryszard, eds. (1990 ). Machine Learning: an Artificial Intelligence Approach. Vol. III. San Mateo, Calif.: Morgan Kaufman. ISBN 0-934613-09-5. OCLC 893488404.
Kolata, G. (1982 ). « How can computer systems get typical sense? ». Science. 217 (4566 ): 1237-1238. Bibcode:1982 Sci … 217.1237 K. doi:10.1126/ science.217.4566.1237. PMID 17837639.
Maker, Meg Houston (2006 ). « AI@50: AI Past, Present, Future ». Dartmouth College. Archived from the initial on 3 January 2007. Retrieved 16 October 2008.
Marcus, Gary; Davis, Ernest (2019 ). Rebooting AI: Building Artificial Intelligence We Can Trust. New York City: Pantheon Books. ISBN 9781524748258. OCLC 1083223029.
Marcus, Gary (2020 ), The Next Decade in AI: Four Steps Towards Robust Expert system, arXiv:2002.06177.
McCarthy, John (1959 ). PROGRAMS WITH GOOD SENSE. Symposium on Mechanization of Thought Processes. NATIONAL PHYSICAL LABORATORY, TEDDINGTON, UK. p. 8.
McCarthy, John; Hayes, Patrick (1969 ). « Some Philosophical Problems From the Standpoint of Expert System ». Machine Intelligence 4. B. Meltzer, Donald Michie (eds.): 463-502.
McCorduck, Pamela (2004 ), Machines Who Think (second ed.), Natick, Massachusetts: A. K. Peters, ISBN 1-5688-1205-1.
Michalski, Ryszard; Carbonell, Jaime; Mitchell, Tom, eds. (1983 ). Machine Learning: an Artificial Intelligence Approach. Vol. I. Palo Alto, Calif.: Tioga Publishing Company. ISBN 0-935382-05-4. OCLC 9262069.
Michalski, Ryszard; Carbonell, Jaime; Mitchell, Tom, eds. (1986 ). Machine Learning: an Expert System Approach. Vol. II. Los Altos, Calif.: Morgan Kaufman. ISBN 0-934613-00-1.
Newell, Allen; Simon, Herbert A. (1972 ). Human Problem Solving (1st ed.). Englewood Cliffs, New Jersey: Prentice Hall. ISBN 0-13-445403-0.
Newell, Allen; Simon, H. A. (1976 ). « Computer Science as Empirical Inquiry: Symbols and Search ». Communications of the ACM. 19 (3 ): 113-126. doi:10.1145/ 360018.360022.
Nilsson, Nils (1998 ). Expert system: A New Synthesis. Morgan Kaufmann. ISBN 978-1-55860-467-4. Archived from the original on 26 July 2020. Retrieved 18 November 2019.
Olazaran, Mikel (1993-01-01), « A Sociological History of the Neural Network Controversy », in Yovits, Marshall C. (ed.), Advances in Computers Volume 37, vol. 37, Elsevier, pp. 335-425, doi:10.1016/ S0065-2458( 08 )60408-8, ISBN 9780120121373, obtained 2023-10-31.
Pearl, J. (1988 ). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. San Mateo, California: Morgan Kaufmann. ISBN 978-1-55860-479-7. OCLC 249625842.
Russell, Stuart J.; Norvig, Peter (2021 ). Artificial Intelligence: A Modern Approach (4th ed.). Hoboken: Pearson. ISBN 978-0-13-461099-3. LCCN 20190474.
Rossi, Francesca (2022-07-06). « AAAI2022: Thinking Fast and Slow in AI (AAAI 2022 Invited Talk) ». Retrieved 2022-07-06.
Selman, Bart (2022-07-06). « AAAI2022: Presidential Address: The State of AI ». Retrieved 2022-07-06.
Serafini, Luciano; Garcez, Artur d’Avila (2016-07-07), Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge, arXiv:1606.04422.
Spiegelhalter, David J.; Dawid, A. Philip; Lauritzen, Steffen; Cowell, Robert G. (1993 ). « Bayesian analysis in professional systems ». Statistical Science. 8 (3 ).
Turing, A. M. (1950 ). « I.-Computing Machinery and Intelligence ». Mind. LIX (236 ): 433-460. doi:10.1093/ mind/LIX.236.433. ISSN 0026-4423. Retrieved 2022-09-14.
Valiant, Leslie G (2008 ). « Knowledge Infusion: In Pursuit of Robustness in Artificial Intelligence ». In Hariharan, R.; Mukund, M.; Vinay, V. (eds.). Foundations of Software Technology and Theoretical Computer Science (Bangalore). pp. 415-422.
Xifan Yao; Jiajun Zhou; Jiangming Zhang; Claudio R. Boer (2017 ). From Intelligent Manufacturing to Smart Manufacturing for Industry 4.0 Driven by Next Generation Artificial Intelligence and Further On.