20 August 1992 Training product unit neural networks with genetic algorithms
Author Affiliations +
Abstract
This paper discusses the training of product neural networks using genetic algorithms. Two unusual techniques are combined; product units are employed in addition to the traditional summing units and a genetic algorithm is used to train the network rather than using backpropagation. As an example, a neural network is trained to calculate the optimum width of transistors in a CMOS switch. It is shown how local minima can affect the performance of a genetic algorithm, and one method of overcoming this is presented.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
David J. Janson, David J. Janson, James F. Frenzel, James F. Frenzel, } "Training product unit neural networks with genetic algorithms", Proc. SPIE 1706, Adaptive and Learning Systems, (20 August 1992); doi: 10.1117/12.139958; https://doi.org/10.1117/12.139958
PROCEEDINGS
7 PAGES


SHARE
Back to Top