computational intelligence
In plain wordsA 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.
An umbrella term for computational methods modeled loosely on nature, or on the vagueness of human language, that solve problems by learning, adaptation and approximation rather than explicit symbolic reasoning: chiefly 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., 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. and 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., often extended to 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., artificial immune systems and probabilistic methods. James Bezdek's influential 1994 definition called a system computationally intelligent when it works only with low-level numerical data, has pattern-recognition components, does not use knowledge in the symbolic-AI sense, and shows adaptivity and fault tolerance. The term is partly institutional, naming the IEEE Computational Intelligence Society and its conferences and journals. Some authors use it as a synonym for 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., notably David Poole, Alan Mackworth and Randy Goebel's textbook Computational Intelligence (1998), while others contrast it with 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..
The plant's controller was built with computational intelligence methods: a fuzzy rule base tuned by a genetic algorithm.
Origin
The earliest widely cited use is the title of the journal Computational Intelligence, founded in 1985. The IEEE Neural Networks Council (founded 1989) organized the first IEEE World Congress on Computational Intelligence in Orlando in 1994, where Bezdek offered his definition; the council became the IEEE Neural Networks Society in 2001 and was renamed the IEEE Computational Intelligence Society about two years later.
Usage note
Largely overlaps with soft computingsoft computing, n.: A 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.; the difference is mostly one of community and emphasis. The boundary with mainstream machine learning has blurred, since neural networks now dominate both.
Related
- soft computingsoft computing, n.: A 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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
- Bezdek, J. C. (1994). What Is Computational Intelligence? In Zurada, J. M., Marks, R. J. & Robinson, C. J. (eds), Computational Intelligence: Imitating Life. IEEE Press.
- Poole, D., Mackworth, A. & Goebel, R. (1998). Computational Intelligence: A Logical Approach. Oxford University Press.
Mentioned in
machine intelligencemachine intelligence, n.: Intelligence shown by machines; another name for artificial intelligence, preferred by some because it does not suggest that such intelligence is fake., 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., soft computingsoft computing, n.: A 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.