20 August 1992 Training product unit neural networks with genetic algorithms
Author Affiliations +
Proceedings Volume 1706, Adaptive and Learning Systems; (1992); doi: 10.1117/12.139958
Event: Aerospace Sensing, 1992, Orlando, FL, United States
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, 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
KEYWORDS
Genetic algorithms

Neural networks

Gallium

Switches

Transistors

Power supplies

Network architectures

Back to Top