论文信息 - Evolution of neural net architectures by a hierarchical grammar-based genetic system

Evolution of neural net architectures by a hierarchical grammar-based genetic system

We present a hierarchically structured system for the evolution of connectionist systems. Our approach is exemplified by evolution paradigms for neural network topologies and weights. Our descriptions of a network’s connectivity are based on context-free grammars which are used to characterize signal flow from input to output neurons. Evolution of a simple control task gives a first impression about the capabilities of this approach.

Christian Jacob | Jan Rehder

[1] L. Darrell Whitley,et al. Genetic algorithms and neural networks: optimizing connections and connectivity , 1990, Parallel Comput..

[2] Peter M. Todd,et al. Designing Neural Networks using Genetic Algorithms , 1989, ICGA.

[3] Stefan Bornholdt,et al. General asymmetric neural networks and structure design by genetic algorithms: a learning rule for temporal patterns , 1992, Proceedings of IEEE Systems Man and Cybernetics Conference - SMC.

[4] John R. Koza,et al. Genetic generation of both the weights and architecture for a neural network , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.