Loading...
Please wait, while we are loading the content...
Similar Documents
Evolutionary Computation and Its Applications in Neural and Fuzzy Systems
| Content Provider | Open Access Library (OALib) |
|---|---|
| Author | Biaobiao Zhang Yue Wu Jiabin Lu K. -L Du |
| Abstract | Neural networks and fuzzy systems are two soft-computing paradigms for system modelling. Adapting a neural or fuzzy system requires to solve two optimization problems: structural optimization and parametric optimization. Structural optimization is a discrete optimization problem which is very hard to solve using conventional optimization techniques. Parametric optimization can be solved using conventional optimization techniques, but the solution may be easily trapped at a bad local optimum. Evolutionary computation is a general-purpose stochastic global optimization approach under the universally accepted neo-Darwinian paradigm, which is a combination of the classical Darwinian evolutionary theory, the selectionism of Weismann, and the genetics of Mendel. Evolutionary algorithms are a major approach to adaptation and optimization. In this paper, we first introduce evolutionary algorithms with emphasis on genetic algorithms and evolutionary strategies. Other evolutionary algorithms such as genetic programming, evolutionary programming, particle swarm optimization, immune algorithm, and ant colony optimization are also described. Some topics pertaining to evolutionary algorithms are also discussed, and a comparison between evolutionary algorithms and simulated annealing is made. Finally, the application of EAs to the learning of neural networks as well as to the structural and parametric adaptations of fuzzy systems is also detailed. 1. Introduction The adaptation of creatures to their environments results from the interaction of two processes, namely, evolution and learning. Unlike evolution, which is based on the Darwinian model of a species, learning is based on the connectionist model of the brain. Evolution is a slow stochastic process at the population level that determines the basic structures of a species, while learning is a process of gradually improving an individual's adaptation ability to its environment by tuning the structure of the individual. Evolutionary algorithms (EAs) are stochastic search methods inspired by the Darwinian model, while neural networks are learning models based on the connectionist model. Compared to the connectionist model-based learning process, fuzzy systems are a high-level abstraction of human cognition. Neural networks, fuzzy systems, and evolutionary algorithms are the three major soft-computing paradigms for computational intelligence. Neural networks and fuzzy systems are two major approaches to system modeling. Adapting neural networks or fuzzy systems involves the solution of two optimization problems: |
| ISSN | 16879724 |
| Journal | Applied Computational Intelligence and Soft Computing |
| DOI | 10.1155/2011/938240 |
| Publisher | Hindawi Publishing Corporation |
| Publisher Date | 2011-01-01 |
| Access Restriction | Open |
| Content Type | Text |
| Resource Type | Article |
| Subject | Artificial Intelligence Computer Networks and Communications Computational Mechanics Computer Science Applications Civil and Structural Engineering |
