USING GENETIC SEARCH TO EXPLOIT THE EMERGENT BEHAVIOR OF NEURAL NETWORKS

Neural networks are known to exhibit emergent behaviors, but it is often far from easy to exploit these properties for desired ends such as effective machine learning. We demonstrate that a genetic algorithm is capable of discovering how to exploit the abilities of one type of network learning, backpropagation in feedforward networks. Our results show that a network architecture evolved by the genetic algorithm performs better than a large network using backpropagation learning alone when the criterion is correct generalization from a set of examples. This is potentially a powerful method for design of neural networks-design by evolution. © 1990.