neats and scruffies
In plain wordsA 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.
A distinction between two styles of AI research. Neats favor formal, unified frameworks — logic, probability theory, optimization — whose properties can be analyzed and proved, holding that intelligence should be explained by a few elegant principles. Scruffies favor building systems from many special-purpose representations and heuristics, judged by whether they work, holding that intelligence is an irreducibly messy collection of mechanisms. In the 1970s and 1980s the scruffy style was associated with MIT and Yale work on frames, scripts and language understanding, and the neat style with logic-based AI at Stanford and Edinburgh. Probabilistic and statistical methods brought a neat turn from the 1990s, while the success of large, empirically engineered 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. systems has given the contrast new life.
The planner is scruffy engineering — dozens of special cases and no theory — and it still beats the neat solver.
Origin
Usually credited to Roger Schank, who in the 1970s contrasted his natural-language work at Yale with logic-based approaches; the terms first appeared in print in a 1981 paper by the psychologist Robert Abelson, who attributed them to Schank. Nils Nilsson discussed the divide in his 1983 presidential address to the AAAI.
Usage note
The labels describe attitudes rather than formal schools, and most researchers mix both. Stuart RussellStuart Russell, prop. n.: A British computer scientist who co-wrote the standard AI textbook and argues that AI must be redesigned to stay uncertain about what humans want, so that it remains under human control. and Peter NorvigPeter Norvig, prop. n.: An American computer scientist who co-wrote the standard AI textbook, led research at Google, and helped show that simple methods trained on huge amounts of data often beat clever hand-built ones.'s textbook presented the rise of probabilistic methods as a victory for the neats; some read the bitter lessonthe bitter lesson, phr.: The argument, made by AI pioneer Rich Sutton in 2019, that AI has advanced mostly through general methods that use ever more computing power, not by programming in human knowledge. as recasting the debate around computation and scale.
Related
- symbolic AIsymbolic AI, n.: An 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.
- 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.
- frameframe, 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.
- the bitter lessonthe bitter lesson, phr.: The argument, made by AI pioneer Rich Sutton in 2019, that AI has advanced mostly through general methods that use ever more computing power, not by programming in human knowledge.
- 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.
- 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.
Mentioned in
symbolic AIsymbolic AI, n.: An 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., 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., 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., 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., the bitter lessonthe bitter lesson, phr.: The argument, made by AI pioneer Rich Sutton in 2019, that AI has advanced mostly through general methods that use ever more computing power, not by programming in human knowledge.