Computational intelligence: Difference between revisions
Dimitrechus (talk | contribs) mNo edit summary |
Fixed broken Fuzzy Logic Sytems link |
||
Line 1: | Line 1: | ||
'''Computational intelligence (CI)''' is a set of Nature-inspired computational methodologies and approaches to address complex problems of the real world applications to which traditional (first principles, probabilistic, black-box, etc.) methodologies and approaches are ineffective or infeasible. It primarily includes [[Fuzzy logic |
'''Computational intelligence (CI)''' is a set of Nature-inspired computational methodologies and approaches to address complex problems of the real world applications to which traditional (first principles, probabilistic, black-box, etc.) methodologies and approaches are ineffective or infeasible. It primarily includes [[Fuzzy logic]] systems, [[Artificial Neural Network|Neural Networks]] and [[Evolutionary Computation]]. In addition, CI also embraces techniques that stem from the above three or gravitate around one or more of them, such as [[Swarm intelligence]] and [[Artificial immune system]]s which can be seen as a part of [[Evolutionary Computation]]; [[Dempster-Shafer theory]], [[Chaos theory]] and [[Multi-valued logic]] which can be seen as off-springs of [[Fuzzy Logic]] Systems, etc. |
||
The characteristic of 'intelligence' is usually attributed to humans. More recently, many products and items also claim to be 'intelligent'. Intelligence is directly linked to the reasoning and decision making. [[Fuzzy logic]] was introduced in 1965 by Prof. L. A. Zadeh as a tool to formalise and represent the reasoning process and [[fuzzy logic system]]s which are based on [[fuzzy logic]] possess many characteristics attributed to ''intelligence''. Fuzzy logic deals effectively with uncertainty that is common for human reasoning, perception and inference and, contrary to some misconceptions, has a very formal and strict mathematical backbone ('is quite deterministic in itself yet allowing uncertainties to be effectively represented and manipulated by it', so to speak). [[Neural networks]], introduced in 1940s (further developed in 1980s) mimic the human brain and represent a computational mechanism based on a simplified mathematical model of the perceptrons (neurons) and signals that they process. [[Evolutionary computation]], introduced by J. Holland in 1970s and more popular since 1990s mimics the population-based sexual evolution through reproduction of generations. It also mimics genetics in so called [[Genetic Algorithms]]. More recently, [[Swarm Intelligence]] has been proposed and developed that considers evolution of individual's cognitive mimicking the way all living creatures and biological systems behaves; intelligent agents learn from its experience and are independent but in a more realistic fashion, interaction between those agents influences in the evolution of the behaviour's rules of each individual. This latter approach is the most advanced computational intelligence method applied in robots up to date, so-called [[Swarm Robotics]]. |
The characteristic of 'intelligence' is usually attributed to humans. More recently, many products and items also claim to be 'intelligent'. Intelligence is directly linked to the reasoning and decision making. [[Fuzzy logic]] was introduced in 1965 by Prof. L. A. Zadeh as a tool to formalise and represent the reasoning process and [[fuzzy logic system]]s which are based on [[fuzzy logic]] possess many characteristics attributed to ''intelligence''. Fuzzy logic deals effectively with uncertainty that is common for human reasoning, perception and inference and, contrary to some misconceptions, has a very formal and strict mathematical backbone ('is quite deterministic in itself yet allowing uncertainties to be effectively represented and manipulated by it', so to speak). [[Neural networks]], introduced in 1940s (further developed in 1980s) mimic the human brain and represent a computational mechanism based on a simplified mathematical model of the perceptrons (neurons) and signals that they process. [[Evolutionary computation]], introduced by J. Holland in 1970s and more popular since 1990s mimics the population-based sexual evolution through reproduction of generations. It also mimics genetics in so called [[Genetic Algorithms]]. More recently, [[Swarm Intelligence]] has been proposed and developed that considers evolution of individual's cognitive mimicking the way all living creatures and biological systems behaves; intelligent agents learn from its experience and are independent but in a more realistic fashion, interaction between those agents influences in the evolution of the behaviour's rules of each individual. This latter approach is the most advanced computational intelligence method applied in robots up to date, so-called [[Swarm Robotics]]. |
Revision as of 17:06, 9 July 2012
Computational intelligence (CI) is a set of Nature-inspired computational methodologies and approaches to address complex problems of the real world applications to which traditional (first principles, probabilistic, black-box, etc.) methodologies and approaches are ineffective or infeasible. It primarily includes Fuzzy logic systems, Neural Networks and Evolutionary Computation. In addition, CI also embraces techniques that stem from the above three or gravitate around one or more of them, such as Swarm intelligence and Artificial immune systems which can be seen as a part of Evolutionary Computation; Dempster-Shafer theory, Chaos theory and Multi-valued logic which can be seen as off-springs of Fuzzy Logic Systems, etc.
The characteristic of 'intelligence' is usually attributed to humans. More recently, many products and items also claim to be 'intelligent'. Intelligence is directly linked to the reasoning and decision making. Fuzzy logic was introduced in 1965 by Prof. L. A. Zadeh as a tool to formalise and represent the reasoning process and fuzzy logic systems which are based on fuzzy logic possess many characteristics attributed to intelligence. Fuzzy logic deals effectively with uncertainty that is common for human reasoning, perception and inference and, contrary to some misconceptions, has a very formal and strict mathematical backbone ('is quite deterministic in itself yet allowing uncertainties to be effectively represented and manipulated by it', so to speak). Neural networks, introduced in 1940s (further developed in 1980s) mimic the human brain and represent a computational mechanism based on a simplified mathematical model of the perceptrons (neurons) and signals that they process. Evolutionary computation, introduced by J. Holland in 1970s and more popular since 1990s mimics the population-based sexual evolution through reproduction of generations. It also mimics genetics in so called Genetic Algorithms. More recently, Swarm Intelligence has been proposed and developed that considers evolution of individual's cognitive mimicking the way all living creatures and biological systems behaves; intelligent agents learn from its experience and are independent but in a more realistic fashion, interaction between those agents influences in the evolution of the behaviour's rules of each individual. This latter approach is the most advanced computational intelligence method applied in robots up to date, so-called Swarm Robotics.
See also
- Ant colony optimization
- Artificial immune systems
- Chaos theory
- Cuckoo search
- Cognitive robotics
- Developmental robotics
- Evolutionary computation
- Evolutionary robotics
- Expert systems
- Firefly algorithm
- Intelligent agents
- Knowledge-Based Engineering
- Machine learning
- Particle swarm optimisation
- Simulated annealing
- Simulated reality
- Soft computing
- Swarm intelligence
- Synthetic intelligence
- Metaheuristic
Related topics:
- Bioinformatics and Bioengineering
- Computational finance and Computational economics
- Concept mining
- Data mining
- Emergence
- Support vector machine
- Intelligent system
References
- Computational Intelligence: An Introduction by Andries Engelbrecht. Wiley & Sons. ISBN 0-470-84870-7
- Computational Intelligence: A Logical Approach by David Poole, Alan Mackworth, Randy Goebel. Oxford University Press. ISBN 0-19-510270-3
Software
- Computational Intelligence Library (CILib)
- OAT (Optimization Algorithm Toolkit): A set of standard computational intelligence optimization algorithms and problems in Java.
- Evolving Intelligent Systems Toolbox(EST)