Effects of Nonlinear Synapses on the Performance of Multilayer Neural Networks

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.

Cite

Text

Dündar et al. "Effects of Nonlinear Synapses on the Performance of Multilayer Neural Networks." Neural Computation, 1996. doi:10.1162/NECO.1996.8.5.939

Markdown

[Dündar et al. "Effects of Nonlinear Synapses on the Performance of Multilayer Neural Networks." Neural Computation, 1996.](https://mlanthology.org/neco/1996/dundar1996neco-effects/) doi:10.1162/NECO.1996.8.5.939

BibTeX

@article{dundar1996neco-effects,
  title     = {{Effects of Nonlinear Synapses on the Performance of Multilayer Neural Networks}},
  author    = {Dündar, Günhan and Hsu, F.-C. and Rose, K.},
  journal   = {Neural Computation},
  year      = {1996},
  pages     = {939-949},
  doi       = {10.1162/NECO.1996.8.5.939},
  volume    = {8},
  url       = {https://mlanthology.org/neco/1996/dundar1996neco-effects/}
}