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.
KeywordsOutput Neuron Cortex Neuron Neuron Functionality Neural Network Development Neuron Activation Function
Unable to display preview. Download preview PDF.
- Miller, Hedges and Todd, Designing Neural Networks using Genetic Algorithms, Proceedings of the International Conference on Genetic Algorithms, 1989.Google Scholar
- Schiffmann W., Joost M and Werner R, Performance Evaluation of Evolutionarily Created Neural Network Topologies, in: Schwefel H P and M’anner R (eds), Parallel Problem Solving from Nature, Berlin, 1991.Google Scholar
- Whitley D., Starkweather T and Bogart C, Genetic algorithms and neural networks: optimizing connections and connectivity, Parallel Computing, vol 14, 1990.Google Scholar
- Hughes M, Genetic Algorithm Workbench Documentation, Cambridge, 1989.Google Scholar
- Harp S A, Samad T, Genetic Synthesis of Neural Network Architecture, in: Davis L (ed), Handbook of Genetic Algorithms, New York, 1991.Google Scholar
- Koza J R, Rice J P, Genetic generation of both weights and architecture for a neural network, in: Proceedings of the International Joint Conference on Neural Networks, 1991.Google Scholar
- Bornholdt S, Graudenz D, General Asymmetric Neural Networks and Structure Desgin by Genetic Algorithms, Neural Networks, vol. 5, 1992.Google Scholar
- Antonisse H J, A Grammer-Based Genetic Algorithm, in: Rawlins G (ed), Foundations of Genetic Algorithms, San Mateo, 1991.Google Scholar