Back-propagation learning and nonidealities in analog neural network hardware
- 1 January 1991
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 2 (1) , 110-117
- https://doi.org/10.1109/72.80296
Abstract
Experimental results from adaptive learning using an optically controlled neural network are presented. The authors have used example problems in nonlinear system identification and signal prediction, two areas of potential neural network application, to study the capabilities of analog neural hardware. These experiments investigated the effects of a variety of nonidealities typical of analog hardware systems. They show that network using large arrays of nonuniform components can perform analog communications with a much higher degree of accuracy than might be expected given the degree of variation in the network's elements. The effects of other common nonidealities, such as noise, weight quantization, and dynamic range limitations, were also investigated.Keywords
This publication has 7 references indexed in Scilit:
- Amorphous silicon photoconductive arrays for artificial neural networksApplied Optics, 1989
- Increased rates of convergence through learning rate adaptationNeural Networks, 1988
- An optically programmed neural networkPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988
- Learning representations by back-propagating errorsNature, 1986
- VLSI architectures for implementation of neural networksAIP Conference Proceedings, 1986
- Parallel Distributed ProcessingPublished by MIT Press ,1986
- A two-dimensional mapping with a strange attractorCommunications in Mathematical Physics, 1976