soft computing
In plain wordsA group of computing methods, including fuzzy logic, neural networks and evolutionary algorithms, that accept imprecise, approximate answers in exchange for being practical on messy real-world problems.
A family of computational methods that settle for approximate answers where exact ones would be too costly or impossible to obtain, as opposed to 'hard' computing, which requires precise models and precise results. Lotfi Zadeh, who promoted the term, framed its guiding principle as exploiting tolerance for imprecision, uncertainty and partial truth to gain tractability, robustness and low cost. Its usual constituents are fuzzy logicfuzzy logic, n.: A kind of logic that allows degrees of truth, so a statement like 'the room is warm' can be 70 percent true, which helps machines handle vague everyday categories., neural networksneural 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., evolutionary computationevolutionary computation, n.: Problem-solving by simulated evolution, much as breeders improve crops: keep many candidate answers, let the better ones produce slightly altered offspring, drop the worse, and repeat for many rounds. and probabilistic reasoning, later joined by rough sets and swarm intelligenceswarm intelligence, n.: The teamwork that appears when crowds of simple creatures or machines, such as ants, bees or small robots, each respond only to what is nearby, with nobody in charge, yet together solve problems.. A defining theme is hybridization, as in neuro-fuzzy systems that learn fuzzy rules by neural-network training, or genetic algorithmsgenetic algorithm, n.: A problem-solving method that copies natural evolution: many candidate solutions compete, the best are 'bred' by mixing and randomly tweaking them, and over many generations the solutions improve. that tune fuzzy controllers. Soft computing was influential in control engineering, consumer electronics and industrial optimization in the 1990s and 2000s; the label has since declined, while its neural-network component grew into 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..
The washing machine's soft computing controller used fuzzy rules to set the cycle from load weight and dirtiness.
Origin
Usually credited to Lotfi Zadeh, who had introduced fuzzy sets in 1965 and promoted the term in the early 1990s. He founded, and from 1991 directed, the Berkeley Initiative in Soft Computing (BISC) at the University of California, Berkeley, and set out the idea in 'Fuzzy Logic, Neural Networks, and Soft Computing' (Communications of the ACM, 1994).
Usage note
Overlaps heavily with computational intelligencecomputational intelligence, n.: A family of AI methods inspired by nature, such as neural networks, fuzzy logic and evolutionary algorithms, that learn or adapt from numbers rather than following explicit logical rules.. 'Soft' refers to tolerance of imprecision, not to software and not to a lack of rigor.
Related
- fuzzy logicfuzzy logic, n.: A kind of logic that allows degrees of truth, so a statement like 'the room is warm' can be 70 percent true, which helps machines handle vague everyday categories.
- computational intelligencecomputational intelligence, n.: A family of AI methods inspired by nature, such as neural networks, fuzzy logic and evolutionary algorithms, that learn or adapt from numbers rather than following explicit logical rules.
- 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.
- evolutionary computationevolutionary computation, n.: Problem-solving by simulated evolution, much as breeders improve crops: keep many candidate answers, let the better ones produce slightly altered offspring, drop the worse, and repeat for many rounds.
- genetic algorithmgenetic algorithm, n.: A problem-solving method that copies natural evolution: many candidate solutions compete, the best are 'bred' by mixing and randomly tweaking them, and over many generations the solutions improve.
- swarm intelligenceswarm intelligence, n.: The teamwork that appears when crowds of simple creatures or machines, such as ants, bees or small robots, each respond only to what is nearby, with nobody in charge, yet together solve problems.
- 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.
Sources
- Zadeh, L. A. (1994). Fuzzy Logic, Neural Networks, and Soft Computing. Communications of the ACM, 37(3), 77–84.
Mentioned in
computational intelligencecomputational intelligence, n.: A family of AI methods inspired by nature, such as neural networks, fuzzy logic and evolutionary algorithms, that learn or adapt from numbers rather than following explicit logical rules., Lotfi ZadehLotfi Zadeh, prop. n.: An Azerbaijani-born American engineer who invented fuzzy logic, which lets computers reason with vague categories such as 'warm' or 'tall' that are true only to a degree.