Genetic evolution of the topology and weight distribution of neural networks
- 1 January 1994
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 5 (1) , 39-53
- https://doi.org/10.1109/72.265959
Abstract
This paper proposes a system based on a parallel genetic algorithm with enhanced encoding and operational abilities. The system, used to evolve feedforward artificial neural networks, has been applied to two widely different problem areas: Boolean function learning and robot control. It is shown that the good results obtained in both cases are due to two factors: first, the enhanced exploration abilities provided by the search-space reducing evolution of both coding granularity and network topology, and, second, the enhanced exploitational abilities due to a recently proposed cooperative local optimizing genetic operator.Keywords
This publication has 25 references indexed in Scilit:
- Structural optimization for performance-based design in earthquake engineering: Applications of neural networksStructural Safety, 2009
- Genetic algorithms and highly constrained problems: The time-table casePublished by Springer Nature ,2006
- A learning strategy for neural networks based on a modified evolutionary strategyPublished by Springer Nature ,2006
- Parallel genetic packing of rectanglesPublished by Springer Nature ,2006
- Genetic algorithms and punctuated equilibria in VLSIPublished by Springer Nature ,2006
- Optimization using distributed genetic algorithmsPublished by Springer Nature ,2005
- Gannet: Genetic design of a neural net for face recognitionPublished by Springer Nature ,2005
- Fractally configured neural networksNeural Networks, 1991
- Partitioning a graph with a parallel genetic algorithmPublished by Springer Nature ,1991
- Econets: Neural networks that learn in an environmentNetwork: Computation in Neural Systems, 1990