Effects of Nonlinear Synapses on the Performance of Multilayer Neural Networks
- 1 July 1996
- journal article
- Published by MIT Press in Neural Computation
- Vol. 8 (5) , 939-949
- https://doi.org/10.1162/neco.1996.8.5.939
Abstract
The problems arising from the use of nonlinear multipliers in multilayer neural network synapse structures are discussed. The errors arising from the neglect of nonlinearities are shown and the effect of training in eliminating these errors is discussed. A method for predicting the final errors resulting from nonlinearities is described. Our approximate results are compared with the results from circuit simulations of an actual multiplier circuit.Keywords
This publication has 7 references indexed in Scilit:
- Analysis of the effects of quantization in multilayer neural networks using a statistical modelIEEE Transactions on Neural Networks, 1992
- Analysis of effects of quantisation in multilayer neural networks using statistical modelElectronics Letters, 1991
- Back-propagation learning and nonidealities in analog neural network hardwareIEEE Transactions on Neural Networks, 1991
- Programmable analog vector-matrix multipliersIEEE Journal of Solid-State Circuits, 1990
- Analogue circuits for variable-synapse electronic neural networksElectronics Letters, 1987
- Continuous-time MOSFET-C filters in VLSIIEEE Transactions on Circuits and Systems, 1986
- A precise four-quadrant multiplier with subnanosecond responseIEEE Journal of Solid-State Circuits, 1968