Determining Neural Network Hidden Layer Size Using Evolutionary Programming
John R. McDonnell, Don Waagen · Defense Technical Information Center (DTIC) · 1993
This work investigates the application of evolutionary programming, a stochastic search technique, for simultaneously determining the weights and the number of hidden units in a fully-connected, multi-layer neural network. The simulated evolution search paradigm provides a means for optimizing both network structure and weight coefficients. Orthogonal learning is implemented by independently modifying network structure and weight parameters. Different structural level search strategies are investigated by comparing the training processes for the 3-bit parity problem. The results indicate that evolutionary programming provides a robust framework for evolving neural networks. Neural Networks, Evolutionary Programming, Signal Detection