
Ecostepz
Ajouter un commentaireVue d'ensemble
-
Missions postés 0
Description de l'entreprise
Symbolic Expert System
In synthetic intelligence, symbolic synthetic intelligence (likewise referred to as classical expert system or logic-based synthetic intelligence) [1] [2] is the term for the collection of all methods in synthetic intelligence research that are based on high-level symbolic (human-readable) representations of issues, logic and search. [3] Symbolic AI utilized tools such as logic programs, production rules, semantic webs and frames, and it developed applications such as knowledge-based systems (in particular, skilled systems), symbolic mathematics, automated theorem provers, ontologies, the semantic web, and automated planning and scheduling systems. The Symbolic AI paradigm caused influential ideas in search, symbolic shows languages, agents, multi-agent systems, the semantic web, and the strengths and constraints of formal knowledge and reasoning systems.
Symbolic AI was the dominant paradigm of AI research study from the mid-1950s up until the mid-1990s. [4] Researchers in the 1960s and the 1970s were convinced that symbolic techniques would eventually succeed in developing a maker with synthetic general intelligence and considered this the supreme goal of their field. [citation required] An early boom, with early successes such as the Logic Theorist and Samuel’s Checkers Playing Program, led to unrealistic expectations and promises and was followed by the first AI Winter as funding dried up. [5] [6] A 2nd boom (1969-1986) accompanied the increase of expert systems, their guarantee of recording business know-how, and an enthusiastic business welcome. [7] [8] That boom, and some early successes, e.g., with XCON at DEC, was followed once again by later . [8] Problems with problems in knowledge acquisition, maintaining big understanding bases, and brittleness in dealing with out-of-domain issues emerged. Another, second, AI Winter (1988-2011) followed. [9] Subsequently, AI researchers focused on addressing hidden issues in dealing with uncertainty and in knowledge acquisition. [10] Uncertainty was addressed with formal approaches such as hidden Markov models, Bayesian reasoning, and statistical relational learning. [11] [12] Symbolic machine learning attended to the understanding acquisition problem with contributions including Version Space, Valiant’s PAC knowing, Quinlan’s ID3 decision-tree knowing, case-based learning, and inductive reasoning programming to learn relations. [13]
Neural networks, a subsymbolic technique, had actually been pursued from early days and reemerged highly 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 deemed successful up until about 2012: « Until Big Data ended up being commonplace, the basic agreement in the Al community was that the so-called neural-network method was helpless. Systems simply didn’t work that well, compared to other approaches. … A transformation can be found in 2012, when a number of people, including a group of researchers working with Hinton, exercised a method to use the power of GPUs to immensely increase the power of neural networks. » [16] Over the next a number of years, deep learning had amazing success in dealing with vision, speech recognition, speech synthesis, image generation, and maker translation. However, since 2020, as fundamental difficulties with bias, description, comprehensibility, and effectiveness ended up being more apparent with deep knowing approaches; an increasing variety of AI scientists have actually called for combining the very best of both the symbolic and neural network techniques [17] [18] and attending to areas that both approaches have trouble with, such as sensible reasoning. [16]
A brief history of symbolic AI to today day follows below. Period and titles are drawn from Henry Kautz’s 2020 AAAI Robert S. Engelmore Memorial Lecture [19] and the longer Wikipedia post on the History of AI, with dates and titles differing slightly for increased clarity.
The first AI summertime: irrational vitality, 1948-1966
Success at early efforts in AI occurred in 3 primary areas: synthetic neural networks, understanding representation, and heuristic search, adding to high expectations. This area summarizes Kautz’s reprise of early AI history.
Approaches motivated by human or animal cognition or habits
Cybernetic methods tried to reproduce the feedback loops between animals and their environments. A robotic turtle, with sensors, motors for driving and guiding, and seven vacuum tubes for control, based on a preprogrammed neural net, was developed as early as 1948. This work can be viewed as an early precursor to later work in neural networks, reinforcement learning, and situated robotics. [20]
A crucial early symbolic AI program was the Logic theorist, composed by Allen Newell, Herbert Simon and Cliff Shaw in 1955-56, as it was able to prove 38 elementary theorems from Whitehead and Russell’s Principia Mathematica. Newell, Simon, and Shaw later on generalized this work to develop a domain-independent issue solver, GPS (General Problem Solver). GPS fixed issues represented with formal operators by means of state-space search utilizing means-ends analysis. [21]
During the 1960s, symbolic techniques achieved fantastic success at simulating smart habits in structured environments such as game-playing, symbolic mathematics, and theorem-proving. AI research was focused in 4 institutions in the 1960s: Carnegie Mellon University, Stanford, MIT and (later) University of Edinburgh. Each one developed its own style of research study. Earlier methods based on cybernetics or synthetic neural networks were abandoned or pressed into the background.
Herbert Simon and Allen Newell studied human problem-solving abilities and tried to formalize them, and their work laid the foundations of the field of expert system, as well as cognitive science, operations research and management science. Their research study team used the outcomes of psychological experiments to establish programs that simulated the methods that people used to solve problems. [22] [23] This tradition, centered at Carnegie Mellon University would eventually culminate in the development of the Soar architecture in the center 1980s. [24] [25]
Heuristic search
In addition to the highly specialized domain-specific type of knowledge that we will see later used in specialist systems, early symbolic AI scientists found another more general application of knowledge. These were called heuristics, guidelines of thumb that guide a search in appealing instructions: « How can non-enumerative search be useful when the underlying issue is tremendously tough? The method advocated by Simon and Newell is to utilize heuristics: quick algorithms that may stop working on some inputs or output suboptimal services. » [26] Another important advance was to discover a method to apply these heuristics that guarantees an option will be discovered, if there is one, not standing up to the occasional fallibility of heuristics: « The A * algorithm provided a basic frame for total and ideal heuristically guided search. A * is utilized as a subroutine within practically every AI algorithm today however is still no magic bullet; its guarantee of efficiency is purchased the cost of worst-case rapid time. [26]
Early deal with understanding representation and reasoning
Early work covered both applications of formal thinking highlighting first-order reasoning, in addition to efforts to handle common-sense thinking in a less formal way.
Modeling formal thinking with reasoning: the « neats »
Unlike Simon and Newell, John McCarthy felt that devices did not require to mimic the precise mechanisms of human thought, but might instead look for the essence of abstract reasoning and problem-solving with logic, [27] no matter whether individuals used the same algorithms. [a] His lab at Stanford (SAIL) concentrated on using official reasoning to fix a wide range of problems, consisting of understanding representation, planning and knowing. [31] Logic was likewise the focus of the work at the University of Edinburgh and elsewhere in Europe which caused the advancement of the shows language Prolog and the science of reasoning programs. [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 fixing hard problems in vision and natural language processing required ad hoc solutions-they argued that no simple and basic principle (like logic) would record all the aspects of smart behavior. Roger Schank explained their « anti-logic » methods as « shabby » (rather than the « neat » paradigms at CMU and Stanford). [36] [37] Commonsense knowledge bases (such as Doug Lenat’s Cyc) are an example of « scruffy » AI, because they need to be built by hand, one complex principle at a time. [38] [39] [40]
The first AI winter: crushed dreams, 1967-1977
The first AI winter was a shock:
During the very first AI summer, lots of people believed that device intelligence might be attained in simply a couple of years. The Defense Advance Research Projects Agency (DARPA) released programs to support AI research to use AI to solve problems of nationwide security; in specific, to automate the translation of Russian to English for intelligence operations and to produce autonomous tanks for the battlefield. Researchers had actually begun to realize that achieving AI was going to be much more difficult than was expected a decade earlier, but a mix of hubris and disingenuousness led lots of university and think-tank researchers to accept financing with guarantees of deliverables that they must have understood they could not satisfy. By the mid-1960s neither beneficial natural language translation systems nor autonomous tanks had been developed, and a remarkable reaction set in. New DARPA leadership canceled existing AI financing programs.
Outside of the United States, the most fertile ground for AI research study was the United Kingdom. The AI winter in the United Kingdom was spurred on not so much by dissatisfied military leaders as by rival academics who viewed AI researchers as charlatans and a drain on research funding. A teacher of used mathematics, Sir James Lighthill, was commissioned by Parliament to assess the state of AI research in the country. The report stated that all of the issues being worked on in AI would be better managed by scientists from other disciplines-such as applied mathematics. The report also claimed that AI successes on toy issues could never ever scale to real-world applications due to combinatorial explosion. [41]
The 2nd AI summertime: understanding is power, 1978-1987
Knowledge-based systems
As limitations with weak, domain-independent methods ended up being increasingly more apparent, [42] researchers from all three customs began to develop knowledge into AI applications. [43] [7] The knowledge revolution was driven by the awareness that understanding underlies high-performance, domain-specific AI applications.
Edward Feigenbaum stated:
– « In the knowledge lies the power. » [44]
to explain that high efficiency 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 carry out an intricate task well, it must understand a fantastic offer about the world in which it operates.
( 2) A possible extension of that concept, called the Breadth Hypothesis: there are 2 additional abilities essential for smart behavior in unexpected circumstances: drawing on significantly basic understanding, and analogizing to specific however distant understanding. [45]
Success with professional systems
This « understanding transformation » resulted in the development and deployment of professional systems (introduced by Edward Feigenbaum), the very first commercially effective type of AI software. [46] [47] [48]
Key specialist systems were:
DENDRAL, which discovered the structure of natural particles from their chemical formula and mass spectrometer readings.
MYCIN, which detected bacteremia – and suggested additional lab tests, when necessary – by translating laboratory results, patient history, and physician observations. « With about 450 rules, MYCIN was able to perform along with some professionals, and considerably better than junior physicians. » [49] INTERNIST and CADUCEUS which took on internal medicine medical diagnosis. Internist tried to catch the know-how of the chairman of internal medication at the University of Pittsburgh School of Medicine while CADUCEUS might ultimately detect approximately 1000 various diseases.
– GUIDON, which revealed how a knowledge base developed for expert issue resolving could be repurposed for teaching. [50] XCON, to set up VAX computers, a then laborious process that could use up to 90 days. XCON reduced the time to about 90 minutes. [9]
DENDRAL is considered the first professional system that count on knowledge-intensive problem-solving. It is described listed below, by Ed Feigenbaum, from a Communications of the ACM interview, Interview with Ed Feigenbaum:
One of the individuals at Stanford interested in computer-based models of mind was Joshua Lederberg, the 1958 Nobel Prize winner in genes. When I told him I wanted an induction « sandbox », he said, « I have just the one for you. » His laboratory was doing mass spectrometry of amino acids. The question was: how do you go from looking 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 proficient at heuristic search approaches, and he had an algorithm that was proficient at generating the chemical issue space.
We did not have a grandiose vision. We worked bottom up. Our chemist was Carl Djerassi, developer of the chemical behind the birth control pill, and also one of the world’s most respected mass spectrometrists. Carl and his postdocs were world-class experts in mass spectrometry. We began to contribute to their knowledge, developing understanding of engineering as we went along. These experiments totaled up to titrating DENDRAL more and more understanding. The more you did that, the smarter the program became. We had extremely great outcomes.
The generalization was: in the understanding lies the power. That was the huge concept. In my profession that is the big, « Ah ha!, » and it wasn’t the method AI was being done previously. Sounds easy, but it’s most likely AI’s most powerful generalization. [51]
The other expert systems discussed above came after DENDRAL. MYCIN exemplifies the traditional expert system architecture of a knowledge-base of guidelines combined to a symbolic reasoning mechanism, including making use of certainty aspects to manage uncertainty. GUIDON reveals how a specific knowledge base can be repurposed for a second application, tutoring, and is an example of a smart tutoring system, a particular type of knowledge-based application. Clancey revealed that it was not enough simply to use MYCIN’s guidelines for guideline, but that he likewise required to include rules for discussion management and trainee modeling. [50] XCON is substantial since of the millions of dollars it conserved DEC, which activated the expert system boom where most all major corporations in the US had professional systems groups, to capture corporate knowledge, protect it, and automate it:
By 1988, DEC’s AI group had 40 professional systems released, with more on the method. DuPont had 100 in use and 500 in development. Nearly every major U.S. corporation had its own Al group and was either utilizing or examining expert systems. [49]
Chess professional knowledge was encoded in Deep Blue. In 1996, this permitted IBM’s Deep Blue, with the assistance of symbolic AI, to win in a video game of chess versus the world champ at that time, Garry Kasparov. [52]
Architecture of knowledge-based and professional systems
An essential component of the system architecture for all expert systems is the understanding base, which stores facts and rules for problem-solving. [53] The most basic approach for a skilled system understanding base is simply a collection or network of production rules. Production guidelines connect signs in a relationship comparable to an If-Then declaration. The specialist system processes the rules to make reductions and to identify what additional details it needs, i.e. what concerns 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 backwards chaining – from objectives to needed information and requirements – manner. More innovative knowledge-based systems, such as Soar can likewise carry out meta-level thinking, that is reasoning about their own reasoning in regards to deciding how to resolve issues and keeping track of the success of analytical strategies.
Blackboard systems are a 2nd kind of knowledge-based or skilled system architecture. They design a neighborhood of specialists incrementally contributing, where they can, to solve a problem. The issue is represented in multiple levels of abstraction or alternate views. The professionals (understanding sources) offer their services whenever they recognize they can contribute. Potential analytical actions are represented on a program that is upgraded as the problem scenario changes. A controller decides how helpful each contribution is, and who need to make the next analytical action. One example, the BB1 chalkboard architecture [54] was originally inspired by research studies of how people plan to perform numerous tasks in a trip. [55] A development of BB1 was to use the exact same blackboard design to fixing its control issue, i.e., its controller performed meta-level thinking with understanding sources that monitored how well a strategy or the problem-solving was continuing and could switch from one method to another as conditions – such as objectives or times – changed. BB1 has actually been applied in numerous domains: building and construction site planning, smart tutoring systems, and real-time patient monitoring.
The 2nd AI winter, 1988-1993
At the height of the AI boom, companies such as Symbolics, LMI, and Texas Instruments were selling LISP devices specifically targeted to speed up the advancement of AI applications and research. In addition, a number of expert system business, such as Teknowledge and Inference Corporation, were selling professional system shells, training, and speaking with to corporations.
Unfortunately, the AI boom did not last and Kautz best describes the 2nd AI winter season that followed:
Many reasons can be used for the arrival of the 2nd AI winter season. The hardware companies stopped working when a lot more affordable basic Unix workstations from Sun together with good compilers for LISP and Prolog came onto the market. Many commercial implementations of expert systems were discontinued when they showed too costly to keep. Medical professional systems never captured on for several factors: the trouble in keeping them as much as date; the challenge for physician to find out how to utilize a bewildering variety of different expert systems for various medical conditions; and maybe most crucially, the hesitation of physicians to rely on a computer-made medical diagnosis over their gut impulse, even for specific domains where the professional systems might outperform an average doctor. Venture capital money deserted AI virtually over night. The world AI conference IJCAI hosted an enormous and extravagant trade convention and countless nonacademic guests in 1987 in Vancouver; the primary AI conference the list below year, AAAI 1988 in St. Paul, was a little and strictly scholastic affair. [9]
Adding in more rigorous structures, 1993-2011
Uncertain reasoning
Both statistical methods and extensions to logic were tried.
One statistical method, hidden Markov designs, had already been popularized in the 1980s for speech acknowledgment work. [11] Subsequently, in 1988, Judea Pearl promoted making use of Bayesian Networks as a noise but efficient way of handling uncertain reasoning with his publication of the book Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. [56] and Bayesian approaches were applied successfully in specialist systems. [57] Even later, in the 1990s, analytical relational knowing, a technique that integrates likelihood with logical solutions, permitted probability to be combined with first-order reasoning, 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 might be utilized with reality maintenance systems. A reality maintenance system tracked assumptions and justifications for all inferences. It enabled reasonings to be withdrawn when assumptions were learnt to be incorrect or a contradiction was obtained. Explanations could be attended to a reasoning by discussing which guidelines were used to create it and then continuing through underlying inferences and guidelines all the method back to root presumptions. [58] Lofti Zadeh had actually introduced a different sort of extension to manage the representation of vagueness. For instance, in deciding how « heavy » or « tall » a man is, there is often no clear « yes » or « no » answer, and a predicate for heavy or high would instead return values between 0 and 1. Those worths represented to what degree the predicates were real. His fuzzy logic even more provided a way for propagating combinations of these worths through rational formulas. [59]
Machine learning
Symbolic maker finding out techniques were investigated to address the knowledge acquisition traffic jam. One of the earliest is Meta-DENDRAL. Meta-DENDRAL used a generate-and-test method to produce plausible guideline hypotheses to test versus spectra. Domain and task knowledge minimized the variety of candidates tested to a workable size. Feigenbaum explained Meta-DENDRAL as
… the culmination of my imagine the early to mid-1960s relating to theory formation. The conception was that you had an issue solver like DENDRAL that took some inputs and produced an output. In doing so, it used layers of knowledge to steer and prune the search. That knowledge acted due to the fact that we spoke with people. But how did individuals get the knowledge? By taking a look at thousands of spectra. So we desired a program that would take a look at countless spectra and infer the knowledge of mass spectrometry that DENDRAL could use to solve specific hypothesis formation issues. We did it. We were even able to publish brand-new understanding of mass spectrometry in the Journal of the American Chemical Society, providing credit only in a footnote that a program, Meta-DENDRAL, in fact did it. We had the ability to do something that had actually been a dream: to have a computer system program developed a new and publishable piece of science. [51]
In contrast to the knowledge-intensive technique of Meta-DENDRAL, Ross Quinlan developed a domain-independent method to analytical category, choice tree knowing, starting first with ID3 [60] and then later on extending its capabilities to C4.5. [61] The decision trees created are glass box, interpretable classifiers, with human-interpretable category rules.
Advances were made in comprehending device learning theory, too. Tom Mitchell introduced variation space knowing which explains learning as a search through an area of hypotheses, with upper, more basic, and lower, more particular, boundaries encompassing all viable hypotheses constant with the examples seen so far. [62] More formally, Valiant presented Probably Approximately Correct Learning (PAC Learning), a framework for the mathematical analysis of maker learning. [63]
Symbolic device learning incorporated more than finding out by example. E.g., John Anderson offered a cognitive design of human knowing where ability practice results in a compilation of guidelines from a declarative format to a procedural format with his ACT-R cognitive architecture. For instance, a trainee may find out to use « Supplementary angles are two angles whose measures sum 180 degrees » as a number of different procedural rules. E.g., one guideline may say that if X and Y are supplementary and you understand X, then Y will be 180 – X. He called his approach « knowledge compilation ». ACT-R has actually been utilized effectively to model elements of human cognition, such as learning and retention. ACT-R is likewise used in intelligent tutoring systems, called cognitive tutors, to successfully teach geometry, computer programs, and algebra to school children. [64]
Inductive reasoning programs was another method to finding out that allowed reasoning programs to be synthesized from input-output examples. E.g., Ehud Shapiro’s MIS (Model Inference System) could manufacture Prolog programs from examples. [65] John R. Koza applied hereditary algorithms to program synthesis to create hereditary programs, which he used to manufacture LISP programs. Finally, Zohar Manna and Richard Waldinger supplied a more general approach to program synthesis that manufactures a functional program in the course of showing its requirements to be appropriate. [66]
As an option to logic, Roger Schank introduced case-based reasoning (CBR). The CBR approach outlined in his book, Dynamic Memory, [67] focuses initially on keeping in mind essential analytical cases for future use and generalizing them where proper. When faced with a brand-new issue, CBR recovers the most similar previous case and adjusts it to the specifics of the existing issue. [68] Another alternative to logic, genetic algorithms and genetic shows are based upon an evolutionary model of knowing, where sets of rules are encoded into populations, the guidelines govern the behavior of people, and choice of the fittest prunes out sets of inappropriate guidelines over numerous generations. [69]
Symbolic maker learning was used to learning ideas, guidelines, heuristics, and problem-solving. Approaches, besides those above, consist of:
1. Learning from guideline or advice-i.e., taking human instruction, posed as advice, and identifying how to operationalize it in specific scenarios. For instance, in a video game of Hearts, discovering precisely how to play a hand to « prevent taking points. » [70] 2. Learning from exemplars-improving performance by accepting subject-matter professional (SME) feedback during training. When problem-solving stops working, querying the expert to either learn a new exemplar for analytical or to learn a new explanation regarding precisely why one prototype is more relevant than another. For instance, the program Protos found out to detect tinnitus cases by communicating with an audiologist. [71] 3. Learning by analogy-constructing issue services based upon comparable issues seen in the past, and after that modifying their solutions to fit a brand-new situation or domain. [72] [73] 4. Apprentice knowing systems-learning unique options to issues by observing human analytical. Domain knowledge discusses why novel solutions are proper and how the option can be generalized. LEAP learned how to create VLSI circuits by observing human designers. [74] 5. Learning by discovery-i.e., developing tasks to perform experiments and after that discovering from the results. Doug Lenat’s Eurisko, for instance, found out heuristics to beat human gamers at the Traveller role-playing game for 2 years in a row. [75] 6. Learning macro-operators-i.e., looking for helpful macro-operators to be discovered from sequences of fundamental problem-solving actions. Good macro-operators simplify analytical by permitting issues to be resolved at a more abstract level. [76]
Deep learning and neuro-symbolic AI 2011-now
With the increase of deep learning, the symbolic AI approach has actually been compared to deep knowing as complementary « … with parallels having been drawn often times by AI researchers between Kahneman’s research study on human reasoning and decision making – reflected in his book Thinking, Fast and Slow – and the so-called « AI systems 1 and 2″, which would in concept be modelled by deep learning and symbolic thinking, respectively. » In this view, symbolic reasoning is more apt for deliberative reasoning, preparation, and description while deep knowing is more apt for fast pattern acknowledgment in perceptual applications with noisy data. [17] [18]
Neuro-symbolic AI: incorporating neural and symbolic approaches
Neuro-symbolic AI efforts to integrate neural and symbolic architectures in a manner that addresses strengths and weak points of each, in a complementary fashion, in order to support robust AI efficient in thinking, finding out, and cognitive modeling. As argued by Valiant [77] and numerous others, [78] the efficient construction of rich computational cognitive designs demands the mix of sound symbolic thinking and efficient (maker) knowing models. Gary Marcus, similarly, argues that: « We can not construct rich cognitive models in a sufficient, automated method without the triumvirate of hybrid architecture, abundant prior understanding, and advanced methods for reasoning. », [79] and in particular: « To construct a robust, knowledge-driven approach to AI we need to have the machinery of symbol-manipulation in our toolkit. Too much of helpful 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 control such abstract knowledge reliably is the apparatus of sign manipulation. » [80]
Henry Kautz, [19] Francesca Rossi, [81] and Bart Selman [82] have likewise argued for a synthesis. Their arguments are based upon a need to attend to the 2 type of thinking talked about in Daniel Kahneman’s book, Thinking, Fast and Slow. Kahneman explains human thinking as having two elements, System 1 and System 2. System 1 is quickly, automatic, instinctive and unconscious. System 2 is slower, step-by-step, and explicit. System 1 is the kind utilized for pattern acknowledgment while System 2 is far much better suited for preparation, reduction, and deliberative thinking. In this view, deep knowing best models the first sort of thinking while symbolic reasoning finest models the 2nd kind and both are required.
Garcez and Lamb explain research study in this location as being continuous for a minimum of the past twenty years, [83] dating from their 2002 book on neurosymbolic learning systems. [84] A series of workshops on neuro-symbolic thinking has actually been held every year given that 2005, see http://www.neural-symbolic.org/ for information.
In their 2015 paper, Neural-Symbolic Learning and Reasoning: Contributions and Challenges, Garcez et al. argue that:
The combination of the symbolic and connectionist paradigms of AI has been pursued by a relatively small research community over the last 2 years and has yielded several substantial outcomes. Over the last decade, neural symbolic systems have been shown capable of conquering the so-called propositional fixation of neural networks, as McCarthy (1988) put it in reaction to Smolensky (1988 ); see also (Hinton, 1990). Neural networks were revealed capable of representing modal and temporal logics (d’Avila Garcez and Lamb, 2006) and fragments of first-order reasoning (Bader, Hitzler, Hölldobler, 2008; d’Avila Garcez, Lamb, Gabbay, 2009). Further, neural-symbolic systems have been used to a variety of issues in the locations of bioinformatics, control engineering, software application confirmation and adaptation, visual intelligence, ontology knowing, and video game. [78]
Approaches for integration are differed. Henry Kautz’s taxonomy of neuro-symbolic architectures, together with some examples, follows:
– Symbolic Neural symbolic-is the existing method of numerous neural models in natural language processing, where words or subword tokens are both the ultimate input and output of big language models. Examples consist of BERT, RoBERTa, and GPT-3.
– Symbolic [Neural] -is exhibited by AlphaGo, where symbolic strategies are utilized to call neural strategies. In this case the symbolic technique is Monte Carlo tree search and the neural strategies find out how to examine game positions.
– Neural|Symbolic-uses a neural architecture to analyze affective data as signs and relationships that are then reasoned about symbolically.
– Neural: Symbolic → Neural-relies on symbolic thinking to produce or label training information that is subsequently learned by a deep knowing design, e.g., to train a neural model for symbolic computation by utilizing a Macsyma-like symbolic mathematics system to create or identify examples.
– Neural _ Symbolic -utilizes a neural web 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 produced from knowledge base rules and terms. Logic Tensor Networks [86] likewise fall into this classification.
– Neural [Symbolic] -allows a neural design to directly call a symbolic reasoning engine, e.g., to perform an action or examine a state.
Many essential research concerns remain, 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 sensible knowledge be found out and reasoned about?
– How can abstract knowledge that is difficult to encode realistically be handled?
Techniques and contributions
This area provides an introduction of strategies and contributions in a total context causing many other, more in-depth articles in Wikipedia. Sections on Machine Learning and Uncertain Reasoning are covered earlier in the history section.
AI programs languages
The key AI programming language in the US during the last symbolic AI boom duration was LISP. LISP is the 2nd earliest programming language after FORTRAN and was developed in 1958 by John McCarthy. LISP supplied the very first read-eval-print loop to support quick program advancement. Compiled functions could be easily blended with interpreted functions. Program tracing, stepping, and breakpoints were likewise provided, along with the capability to alter values or functions and continue from breakpoints or mistakes. It had the first self-hosting compiler, indicating that the compiler itself was originally composed in LISP and after that ran interpretively to compile the compiler code.
Other crucial developments pioneered by LISP that have infected other shows languages consist of:
Garbage collection
Dynamic typing
Higher-order functions
Recursion
Conditionals
Programs were themselves data structures that other programs could operate on, enabling the easy definition of higher-level languages.
In contrast to the US, in Europe the essential AI programs language throughout that very same period was Prolog. Prolog provided an integrated store of facts and provisions that could be queried by a read-eval-print loop. The shop could function as a knowledge base and the provisions might function as rules or a limited kind of reasoning. As a subset of first-order logic Prolog was based upon Horn stipulations with a closed-world assumption-any realities not understood were thought about false-and an unique name assumption for primitive terms-e.g., the identifier barack_obama was considered to describe exactly one object. Backtracking and marriage are built-in to Prolog.
Alain Colmerauer and Philippe Roussel are credited as the inventors of Prolog. Prolog is a kind of logic shows, which was developed by Robert Kowalski. Its history was likewise affected by Carl Hewitt’s PLANNER, an assertional database with pattern-directed invocation of techniques. For more detail see the area on the origins of Prolog in the PLANNER article.
Prolog is likewise a type of declarative programs. The logic provisions that explain programs are directly interpreted to run the programs defined. No explicit series of actions is needed, as is the case with essential programs languages.
Japan promoted Prolog for its Fifth Generation Project, planning to develop unique hardware for high efficiency. Similarly, LISP devices were developed to run LISP, but as the second AI boom turned to bust these companies could not complete with brand-new workstations that might now run LISP or Prolog natively at equivalent speeds. See the history area for more information.
Smalltalk was another influential AI shows language. For example, it presented metaclasses and, along with Flavors and CommonLoops, affected the Common Lisp Object System, or (CLOS), that is now part of Common Lisp, the present standard Lisp dialect. CLOS is a Lisp-based object-oriented system that allows numerous inheritance, in addition to incremental extensions to both classes and metaclasses, hence providing a run-time meta-object procedure. [88]
For other AI shows languages see this list of programs languages for expert system. Currently, Python, a multi-paradigm shows language, is the most popular shows language, partially due to its comprehensive package library that supports data science, natural language processing, and deep knowing. Python includes a read-eval-print loop, functional aspects such as higher-order functions, and object-oriented programs that includes metaclasses.
Search
Search emerges in lots of type of issue fixing, including preparation, restriction satisfaction, and playing video games such as checkers, chess, and go. The finest 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 video games, alpha-beta pruning, branch and bound, and minimax were early contributions.
Knowledge representation and reasoning
Multiple different approaches to represent knowledge and after that reason with those representations have actually been investigated. Below is a fast summary of techniques to knowledge representation and automated reasoning.
Knowledge representation
Semantic networks, conceptual graphs, frames, and reasoning are all methods to modeling knowledge such as domain knowledge, problem-solving understanding, and the semantic meaning of language. Ontologies design essential concepts 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 deemed an ontology. YAGO includes WordNet as part of its ontology, to align realities drawn out from Wikipedia with WordNet synsets. The Disease Ontology is an example of a medical ontology currently being utilized.
Description reasoning is a reasoning for automated category of ontologies and for detecting irregular classification data. 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 check consistency with deductive classifiers such as such as HermiT. [89]
First-order reasoning is more basic than description logic. The automated theorem provers talked about below can show theorems in first-order logic. Horn stipulation logic is more restricted than first-order reasoning and is used in logic programming languages such as Prolog. Extensions to first-order logic include temporal logic, to deal with time; epistemic reasoning, to reason about representative knowledge; modal reasoning, to deal with possibility and necessity; and probabilistic logics to manage reasoning and likelihood together.
Automatic theorem proving
Examples of automated theorem provers for first-order logic are:
Prover9.
ACL2.
Vampire.
Prover9 can be utilized in combination with the Mace4 design checker. ACL2 is a theorem prover that can deal with evidence by induction and is a descendant of the Boyer-Moore Theorem Prover, likewise referred to as Nqthm.
Reasoning in knowledge-based systems
Knowledge-based systems have an explicit knowledge base, usually of guidelines, to improve reusability throughout domains by separating procedural code and domain knowledge. A separate inference engine processes rules and adds, deletes, or customizes a knowledge store.
Forward chaining inference engines are the most typical, and are seen in CLIPS and OPS5. Backward chaining occurs in Prolog, where a more minimal sensible representation is utilized, Horn Clauses. Pattern-matching, particularly unification, is used in Prolog.
A more flexible type of analytical takes place when reasoning about what to do next occurs, instead of just selecting one of the available actions. This type of meta-level reasoning is utilized in Soar and in the BB1 blackboard architecture.
Cognitive architectures such as ACT-R may have extra abilities, such as the ability to assemble frequently used knowledge into higher-level portions.
Commonsense thinking
Marvin Minsky first proposed frames as a way of analyzing common visual situations, such as an office, and Roger Schank extended this concept to scripts for typical routines, such as dining out. Cyc has actually tried to record helpful common-sense knowledge and has « micro-theories » to manage particular kinds of domain-specific reasoning.
Qualitative simulation, such as Benjamin Kuipers’s QSIM, [90] estimates human reasoning about naive physics, such as what takes place when we warm a liquid in a pot on the range. We expect it to heat and possibly boil over, although we may not understand its temperature, its boiling point, or other details, such as climatic pressure.
Similarly, Allen’s temporal interval algebra is a simplification of thinking 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 reasoning
Constraint solvers perform a more minimal sort of inference than first-order logic. They can simplify sets of spatiotemporal restrictions, such as those for RCC or Temporal Algebra, in addition to solving other type of puzzle problems, such as Wordle, Sudoku, cryptarithmetic issues, and so on. Constraint reasoning programming can be used to resolve scheduling issues, for instance with restriction handling rules (CHR).
Automated planning
The General Problem Solver (GPS) cast preparation as problem-solving used means-ends analysis to produce strategies. STRIPS took a various approach, seeing planning as theorem proving. Graphplan takes a least-commitment method to preparation, rather than sequentially picking actions from a preliminary state, working forwards, or a goal state if working in reverse. Satplan is a method to planning where a planning problem is minimized to a Boolean satisfiability problem.
Natural language processing
Natural language processing focuses on dealing with language as information to perform jobs such as identifying topics without necessarily understanding the desired meaning. Natural language understanding, on the other hand, constructs a significance representation and uses that for more processing, such as answering 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, but since improved by deep knowing approaches. In symbolic AI, discourse representation theory and first-order reasoning have actually been used to represent sentence meanings. Latent semantic analysis (LSA) and specific semantic analysis also supplied vector representations of documents. In the latter case, vector elements are interpretable as principles called by Wikipedia short articles.
New deep learning approaches based upon Transformer models have actually now eclipsed these earlier symbolic AI approaches and obtained advanced efficiency in natural language processing. However, Transformer models are nontransparent and do not yet produce human-interpretable semantic representations for sentences and documents. Instead, they produce task-specific vectors where the meaning of the vector parts is opaque.
Agents and multi-agent systems
Agents are self-governing systems embedded in an environment they view and act upon in some sense. Russell and Norvig’s standard book on synthetic intelligence is arranged to show agent architectures of increasing sophistication. [91] The sophistication of representatives varies from basic reactive representatives, to those with a model of the world and automated planning abilities, potentially a BDI agent, i.e., one with beliefs, desires, and intents – or additionally a support learning model found out in time to choose actions – as much as a mix of alternative architectures, such as a neuro-symbolic architecture [87] that includes deep learning for perception. [92]
On the other hand, a multi-agent system includes numerous representatives that communicate among themselves with some inter-agent communication language such as Knowledge Query and Manipulation Language (KQML). The agents need not all have the same internal architecture. Advantages of multi-agent systems consist of the ability to divide work amongst the representatives and to increase fault tolerance when agents are lost. Research issues consist of how agents reach consensus, dispersed issue fixing, multi-agent learning, multi-agent preparation, and dispersed constraint optimization.
Controversies arose from at an early stage 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 but declined symbolic approaches-primarily connectionists-and those outside the field. Critiques from beyond the field were mainly from philosophers, on intellectual grounds, however likewise from funding companies, especially throughout the two AI winters.
The Frame Problem: understanding representation difficulties for first-order logic
Limitations were discovered in using simple first-order reasoning to factor about dynamic domains. Problems were found both with regards to mentioning the preconditions for an action to prosper and in offering 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 Expert System. » [93] An easy example happens in « showing that a person individual could get into discussion with another », as an axiom asserting « if an individual has a telephone he still has it after looking up a number in the telephone book » would be needed for the reduction to be successful. Similar axioms would be required for other domain actions to specify what did not alter.
A similar issue, called the Qualification Problem, happens in attempting to specify the prerequisites for an action to prosper. A limitless number of pathological conditions can be pictured, e.g., a banana in a tailpipe could avoid an automobile from operating correctly.
McCarthy’s approach to repair the frame issue was circumscription, a sort of non-monotonic logic where reductions might be made from actions that require just specify what would change while not having to clearly specify everything that would not change. Other non-monotonic reasonings offered truth maintenance systems that revised beliefs leading to contradictions.
Other methods of dealing with more open-ended domains included probabilistic thinking systems and device learning to discover brand-new concepts and rules. McCarthy’s Advice Taker can be deemed an inspiration here, as it could integrate new knowledge offered by a human in the kind of assertions or guidelines. For example, experimental symbolic machine learning systems checked out the ability to take high-level natural language guidance and to translate it into domain-specific actionable guidelines.
Similar to the problems in managing dynamic domains, common-sense thinking is also hard to record in official thinking. Examples of sensible thinking include implicit reasoning about how individuals think or general knowledge of daily events, items, and living creatures. This kind of knowledge is taken for approved and not viewed as noteworthy. Common-sense reasoning is an open location of research and challenging both for symbolic systems (e.g., Cyc has attempted to capture key parts of this understanding over more than a years) and neural systems (e.g., self-driving automobiles that do not understand not to drive into cones or not to hit pedestrians strolling a bicycle).
McCarthy viewed his Advice Taker as having common-sense, but his definition of common-sense was different than the one above. [94] He specified a program as having good sense « if it immediately deduces for itself a sufficiently broad class of instant repercussions of anything it is informed and what it currently understands. «
Connectionist AI: philosophical challenges and sociological disputes
Connectionist approaches include earlier work on neural networks, [95] such as perceptrons; operate 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 advanced methods, such as Transformers, GANs, and other operate in deep learning.
Three philosophical positions [96] have been described among connectionists:
1. Implementationism-where connectionist architectures implement the capabilities for symbolic processing,
2. Radical connectionism-where symbolic processing is turned down completely, and connectionist architectures underlie intelligence and are totally adequate to discuss it,
3. Moderate connectionism-where symbolic processing and connectionist architectures are viewed as complementary and both are needed for intelligence
Olazaran, in his sociological history of the debates within the neural network community, described the moderate connectionism view as essentially suitable with present research study in neuro-symbolic hybrids:
The 3rd and last position I wish to examine here is what I call the moderate connectionist view, a more diverse view of the current dispute in between connectionism and symbolic AI. Among the researchers who has elaborated this position most clearly 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 (a minimum of) 2 type of theories are required in order to study and design cognition. On the one hand, for some information-processing jobs (such as pattern acknowledgment) connectionism has advantages over symbolic models. But on the other hand, for other cognitive procedures (such as serial, deductive thinking, and generative sign adjustment processes) the symbolic paradigm provides adequate models, and not just « approximations » (contrary to what radical connectionists would claim). [97]
Gary Marcus has declared that the animus in the deep learning neighborhood versus symbolic approaches now might be more sociological than philosophical:
To think that we can simply abandon symbol-manipulation is to suspend disbelief.
And yet, for the a lot of part, that’s how most existing AI profits. Hinton and lots of others have actually tried tough to banish symbols altogether. The deep learning hope-seemingly grounded not so much in science, but in a sort of historical grudge-is that intelligent habits will emerge purely from the confluence of massive data and deep knowing. Where classical computers and software resolve jobs by specifying sets of symbol-manipulating guidelines committed to specific tasks, such as editing a line in a word processor or performing a calculation in a spreadsheet, neural networks typically try to fix jobs by analytical approximation and gaining from examples.
According to Marcus, Geoffrey Hinton and his colleagues have been vehemently « anti-symbolic »:
When deep knowing reemerged in 2012, it was with a type of take-no-prisoners mindset that has identified most of the last decade. By 2015, his hostility towards all things signs had totally crystallized. He offered a talk at an AI workshop at Stanford comparing signs to aether, one of science’s greatest errors.
…
Ever since, his anti-symbolic project has actually just increased in intensity. In 2016, Yann LeCun, Bengio, and Hinton wrote a manifesto for deep knowing in among science’s essential journals, Nature. It closed with a direct attack on symbol control, calling not for reconciliation however for outright replacement. Later, Hinton informed a gathering of European Union leaders that investing any more money in symbol-manipulating approaches was « a big mistake, » likening it to buying internal combustion engines in the age of electrical cars and trucks. [98]
Part of these conflicts may be because of uncertain terms:
Turing award winner Judea Pearl provides a critique of artificial intelligence which, sadly, conflates the terms artificial intelligence and deep learning. Similarly, when Geoffrey Hinton refers to symbolic AI, the undertone of the term tends to be that of professional systems dispossessed of any ability to discover. The use of the terms is in need of explanation. Artificial intelligence is not confined to association guideline mining, c.f. the body of work on symbolic ML and relational knowing (the distinctions to deep learning being the choice of representation, localist logical rather than distributed, and the non-use of gradient-based learning algorithms). Equally, symbolic AI is not practically production rules written by hand. A proper meaning of AI concerns understanding representation and thinking, autonomous multi-agent systems, planning and argumentation, in addition to learning. [99]
Situated robotics: the world as a model
Another critique of symbolic AI is the embodied cognition technique:
The embodied cognition method declares that it makes no sense to consider the brain individually: cognition occurs within a body, which is embedded in an environment. We require to study the system as a whole; the brain’s operating exploits regularities in its environment, including the rest of its body. Under the embodied cognition method, robotics, vision, and other sensing units become central, not peripheral. [100]
Rodney Brooks invented behavior-based robotics, one technique to embodied cognition. Nouvelle AI, another name for this technique, is viewed as an alternative to both symbolic AI and connectionist AI. His method declined representations, either symbolic or dispersed, as not only unneeded, but as harmful. Instead, he produced the subsumption architecture, a layered architecture for embodied agents. Each layer attains a various function and should work in the real life. For instance, the very first robot he describes in Intelligence Without Representation, has three layers. The bottom layer analyzes finder sensing units to avoid things. The middle layer triggers the robot to roam around when there are no barriers. The top layer causes the robot to go to more remote places for additional exploration. Each layer can briefly prevent or reduce a lower-level layer. He criticized AI scientists for defining AI issues for their systems, when: « There is no tidy department in between perception (abstraction) and thinking in the real life. » [101] He called his robots « Creatures » and each layer was « composed of a fixed-topology network of simple finite state machines. » [102] In the Nouvelle AI technique, « First, it is essential to check the Creatures we build in the real life; i.e., in the exact same world that we people live in. It is devastating to fall under the temptation of testing them in a streamlined world first, even with the very best intents of later moving activity to an unsimplified world. » [103] His focus on real-world testing remained in contrast to « Early work in AI focused on games, geometrical problems, symbolic algebra, theorem proving, and other official systems » [104] and using the blocks world in symbolic AI systems such as SHRDLU.
Current views
Each approach-symbolic, connectionist, and behavior-based-has advantages, however has actually been slammed by the other methods. Symbolic AI has actually been criticized as disembodied, responsible to the certification problem, and poor in managing the perceptual issues where deep learning excels. In turn, connectionist AI has been criticized as inadequately suited for deliberative step-by-step problem resolving, integrating knowledge, and dealing with preparation. Finally, Nouvelle AI masters reactive and real-world robotics domains but has actually been criticized for problems in incorporating knowing and understanding.
Hybrid AIs including several of these techniques are currently seen as the path forward. [19] [81] [82] Russell and Norvig conclude that:
Overall, Dreyfus saw locations where AI did not have total answers and said that Al is therefore impossible; we now see many of these same areas undergoing continued research study and development causing increased ability, not impossibility. [100]
Expert system.
Automated preparation and scheduling
Automated theorem proving
Belief modification
Case-based thinking
Cognitive architecture
Cognitive science
Connectionism
Constraint programming
Deep learning
First-order reasoning
GOFAI
History of expert system
Inductive logic programming
Knowledge-based systems
Knowledge representation and thinking
Logic programs
Machine knowing
Model checking
Model-based thinking
Multi-agent system
Natural language processing
Neuro-symbolic AI
Ontology
Philosophy of synthetic intelligence
Physical symbol systems hypothesis
Semantic Web
Sequential pattern mining
Statistical relational knowing
Symbolic mathematics
YAGO ontology
WordNet
Notes
^ McCarthy once said: « This is AI, so we do not care if it’s psychologically real ». [4] McCarthy reiterated his position in 2006 at the AI@50 conference where he stated « Artificial intelligence is not, by meaning, simulation of human intelligence ». [28] Pamela McCorduck writes that there are « 2 significant branches of expert system: one targeted at producing smart behavior no matter how it was achieved, and the other targeted at modeling intelligent procedures found in nature, especially human ones. », [29] Stuart Russell and Peter Norvig composed « Aeronautical engineering texts do not define the objective of their field as making ‘devices that fly so precisely like pigeons that they can trick even other pigeons.' » [30] Citations
^ Garnelo, Marta; Shanahan, Murray (October 2019). « Reconciling deep learning with symbolic artificial intelligence: representing things 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 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. 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 mistakes ». 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 thresholds of understanding ». 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 artificial intelligence? ». IONOS Digitalguide. Retrieved 2021-12-02.
^ Hayes-Roth, Murray & Adelman 2015.
^ Hayes-Roth, Barbara (1985 ). « A chalkboard architecture for control ». Artificial Intelligence. 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 big city ». International Journal of Artificial Intelligence 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 City: 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 Knowing 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 Artificial Intelligence 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 ». Artificial Intelligence. 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 knowledge representation: AI at a deadlock » (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 Technology. Springer US. pp. 351-388. doi:10.1007/ 978-0-585-29599-2_11.
Howe, J. (November 1994). « Expert System 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 ). Artificial intelligence: an Expert System Approach. Vol. III. San Mateo, Calif.: Morgan Kaufman. ISBN 0-934613-09-5. OCLC 893488404.
Kolata, G. (1982 ). « How can computer systems get common 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: Pantheon Books. ISBN 9781524748258. OCLC 1083223029.
Marcus, Gary (2020 ), The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence, 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 (2nd ed.), Natick, Massachusetts: A. K. Peters, ISBN 1-5688-1205-1.
Michalski, Ryszard; Carbonell, Jaime; Mitchell, Tom, eds. (1983 ). Artificial intelligence: an Expert System Approach. Vol. I. Palo Alto, Calif.: Tioga Publishing Company. ISBN 0-935382-05-4. OCLC 9262069.
Michalski, Ryszard; Carbonell, Jaime; Mitchell, Tom, eds. (1986 ). Artificial intelligence: 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 initial 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, recovered 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 ). Expert system: 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 Expert System ». 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 Expert System and Further On.