symbolic AI
In plain wordsAn approach to AI that writes knowledge down as human-readable symbols and rules, such as 'every bird has wings', and reasons by manipulating them step by step instead of learning patterns from data.
The tradition in artificial intelligenceartificial intelligence, n.: Computer systems that do things we would normally credit to a thinking mind, such as holding a conversation, reading an X-ray or planning a route, and the field of research that builds them. that builds intelligent behavior from explicit representations a person can inspect: symbols naming objects, properties and relations, assembled into larger structures — framesframe, n.: In classic AI, a ready-made template for a familiar kind of thing or event, such as a kitchen or a job interview, with blanks to fill in and sensible default values., semantic networkssemantic network, n.: A way of storing knowledge as a web of concepts joined by labeled arrows, such as 'canary — is a — bird' and 'bird — can — fly', so a program can follow the links., if–then rules, logical formulas — and transformed by programs that derive new structures from old ones through deduction, searchstate space search, n.: Solving a problem by treating every situation it could be in as a point on a map, with each possible move as a road between points, and searching for a route from the start to a goal. and planningautomated planning, n.: The branch of AI that works out a sequence of actions to reach a goal, such as the steps a robot must take to assemble a part, from descriptions of what each action needs and what it changes.. Its working hypothesis, made explicit in the physical symbol system hypothesisphysical symbol system hypothesis, n.: The 1976 claim by two AI pioneers that a machine which stores and rearranges symbols according to rules has everything needed for general intelligence, and that anything generally intelligent must be such a machine., is that such manipulation suffices for general intelligence. Strengths include transparency, exact multi-step reasoning, compositional generalization and the ability to encode expert knowledge directly; weaknesses include brittleness outside anticipated cases, difficulty with noisy perception and uncertainty, and the cost of hand-building knowledge (the knowledge acquisition bottleneckknowledge acquisition bottleneck, n.: The problem that getting knowledge out of human experts and into a computer by hand is so slow and costly that it limited how far classic expert systems could go.). It dominated AI research from the 1956 Dartmouth workshopDartmouth workshop, prop. n.: A summer meeting of scientists at Dartmouth College in 1956, planned in a 1955 funding proposal that first used the phrase 'artificial intelligence'. Most histories treat it as the moment AI became a research field of its own. until the late 1980s and survives in SAT solversBoolean satisfiability problem, n.: The puzzle of deciding whether a set of true-or-false conditions can all be met at once. It is famously hard in theory, yet modern solvers routinely handle millions of conditions., planners, theorem provers, knowledge graphsknowledge graph, n.: A huge web of facts stored as connections between things — 'Paris is the capital of France', 'Marie Curie won a Nobel Prize' — that computers can search, combine and reason over. and neuro-symbolic AIneuro-symbolic AI, n.: AI that combines neural networks, which learn patterns from data, with symbolic methods, which follow explicit rules and logic, aiming for systems that both learn flexibly and reason reliably..
Symbolic AI never disappeared; it runs inside chip verifiers, airline crew schedulers and tax software.
Origin
The program began with Allen Newell, Cliff Shaw and Herbert Simon's Logic TheoristLogic Theorist, prop. n.: A 1956 computer program that proved theorems from a classic logic textbook by searching cleverly rather than trying every possibility. Many historians count it as the first AI program. (1956) and John McCarthy's proposal (1958, published 1959) for programs that reason in formal logic. The label 'symbolic AI' has no identified coiner; it became widespread in the 1980s, chiefly as a contrast with connectionismconnectionism, n.: The view that minds and intelligent machines are best built from huge networks of simple, neuron-like units whose connection strengths are learned, rather than from explicit rules and symbols., whose revival with backpropagationbackpropagation, n.: The method neural networks use to learn from mistakes: it works backward from the error to figure out how much each internal connection contributed, so every connection can be adjusted in the right direction. made the distinction salient.
Usage note
Symbolic and statistical methods overlap: Bayesian networksBayesian network, n.: A diagram of causes and effects with probabilities attached — say, how rain and a sprinkler can each make grass wet — that lets a computer update its beliefs about hidden causes when it sees evidence. combine explicit symbols with probabilities. The term is sometimes used as a synonym for good old-fashioned AIgood old-fashioned AI, n.: A nickname for the classic style of AI, dominant from the 1950s to the 1980s, that tried to make computers intelligent by writing knowledge and rules down by hand., which carries a more dismissive tone.
Related
- good old-fashioned AIgood old-fashioned AI, n.: A nickname for the classic style of AI, dominant from the 1950s to the 1980s, that tried to make computers intelligent by writing knowledge and rules down by hand.
- physical symbol system hypothesisphysical symbol system hypothesis, n.: The 1976 claim by two AI pioneers that a machine which stores and rearranges symbols according to rules has everything needed for general intelligence, and that anything generally intelligent must be such a machine.
- knowledge representationknowledge representation, n.: The study of how to record knowledge about objects, categories, rules and events in a precise format, so that a program can reason with it and reach conclusions nobody typed in.
- expert systemexpert system, n.: A program that stores a human specialist's know-how as many if–then rules and uses them to give advice or make decisions in a narrow field, such as diagnosing infections or configuring computers.
- neuro-symbolic AIneuro-symbolic AI, n.: AI that combines neural networks, which learn patterns from data, with symbolic methods, which follow explicit rules and logic, aiming for systems that both learn flexibly and reason reliably.
- neats and scruffiesneats and scruffies, phr.: A joking split of AI researchers into 'neats', who want clean mathematical theories that can be proved correct, and 'scruffies', who build messy collections of tricks that simply work.
- connectionismconnectionism, n.: The view that minds and intelligent machines are best built from huge networks of simple, neuron-like units whose connection strengths are learned, rather than from explicit rules and symbols.
- deep learningdeep learning, n.: Machine learning done with neural networks built from many stacked layers: raw data such as pixels, sound or text goes in at one end, and each layer turns what it receives into something more abstract.
Sources
- Newell, A. & Simon, H. A. (1976). Computer Science as Empirical Inquiry: Symbols and Search. Communications of the ACM 19(3), 113–126.
- McCarthy, J. (1959). Programs with Common Sense. In Mechanisation of Thought Processes. HMSO, London.
Mentioned in
artificial intelligenceartificial intelligence, n.: Computer systems that do things we would normally credit to a thinking mind, such as holding a conversation, reading an X-ray or planning a route, and the field of research that builds them., deep learningdeep learning, n.: Machine learning done with neural networks built from many stacked layers: raw data such as pixels, sound or text goes in at one end, and each layer turns what it receives into something more abstract., machine learningmachine learning, n.: A way of building software that learns from examples instead of following rules written by a programmer. Shown thousands of labeled photos, for instance, a program can learn to recognize cats., neural networkneural network, n.: A kind of computer program that learns a task from examples by tuning thousands to billions of connections between simple number-crunching units, an arrangement loosely inspired by nerve cells in the brain., connectionismconnectionism, n.: The view that minds and intelligent machines are best built from huge networks of simple, neuron-like units whose connection strengths are learned, rather than from explicit rules and symbols., cyberneticscybernetics, n.: The study of how animals, machines and organizations steer themselves using feedback: sensing the result of an action and correcting course. It was both a parent and an early rival of AI., CycCyc, prop. n.: An AI system built by specialists who spent decades typing in millions of everyday truths, such as 'people cannot be in two places at once', hoping to give computers common sense., Dartmouth workshopDartmouth workshop, prop. n.: A summer meeting of scientists at Dartmouth College in 1956, planned in a 1955 funding proposal that first used the phrase 'artificial intelligence'. Most histories treat it as the moment AI became a research field of its own., frame problemframe problem, n.: The difficulty of getting an AI to work out what does and does not change when something happens, without spelling out every one of the countless things that stay the same., Gary MarcusGary Marcus, prop. n.: An American cognitive scientist and leading critic of deep learning, who argues that today's AI cannot reason reliably and needs to be combined with symbolic methods., General Problem SolverGeneral Problem Solver, prop. n.: A 1950s program meant to solve any well-defined puzzle by repeatedly comparing where it was with where it wanted to be and choosing steps that closed the gap., good old-fashioned AIgood old-fashioned AI, n.: A nickname for the classic style of AI, dominant from the 1950s to the 1980s, that tried to make computers intelligent by writing knowledge and rules down by hand., Hubert DreyfusHubert Dreyfus, prop. n.: An American philosopher who argued from the 1960s that computers following explicit rules could never match human intelligence, which rests on bodily, intuitive know-how., John McCarthyJohn McCarthy, prop. n.: The American computer scientist who coined the term 'artificial intelligence', invented the Lisp programming language and championed formal logic as the route to machine common sense., LispLisp, prop. n.: A programming language invented in 1958 for AI research, in which programs and data are written the same way, as nested lists in parentheses. It was the main language of AI for decades., Logic TheoristLogic Theorist, prop. n.: A 1956 computer program that proved theorems from a classic logic textbook by searching cleverly rather than trying every possibility. Many historians count it as the first AI program., Marvin MinskyMarvin Minsky, prop. n.: An American AI pioneer who helped launch the field and MIT's AI laboratory, co-wrote a famous critique of early neural networks, and pictured the mind as a society of many simple parts., neuro-symbolic AIneuro-symbolic AI, n.: AI that combines neural networks, which learn patterns from data, with symbolic methods, which follow explicit rules and logic, aiming for systems that both learn flexibly and reason reliably., Perceptrons (book)Perceptrons (book), prop. n.: A 1969 book by Marvin Minsky and Seymour Papert proving that simple one-layer neural networks cannot learn certain patterns. It is widely blamed for a decade-long slump in neural-network research., physical symbol system hypothesisphysical symbol system hypothesis, n.: The 1976 claim by two AI pioneers that a machine which stores and rearranges symbols according to rules has everything needed for general intelligence, and that anything generally intelligent must be such a machine., Polanyi's paradoxPolanyi's paradox, n.: The observation that we know how to do many things — recognize a face, ride a bike — that we cannot explain in words. That made such skills hard to program until machines learned them from examples., PrologProlog, prop. n.: A programming language from 1972 in which you state facts and rules in logic and then ask questions; the computer finds answers by searching for proofs., reasoningreasoning, n.: Working out conclusions step by step from facts, rules or evidence, as in solving a math problem or planning a trip. Whether today's AI truly reasons, or imitates reasoning, is debated., The Society of MindThe Society of Mind, prop. n.: AI pioneer Marvin Minsky's 1986 book arguing that intelligence comes from huge numbers of tiny, simple processes working together, no one of which is smart by itself.