ML Anthology

The Target Switch Algorithm: A Constructive Learning Procedure for Feed-Forward Neural Networks

Colin Campbell, Conrado J. Pérez Vicente
NeCo 1995 pp. 1245-1264
doi:10.1162/NECO.1995.7.6.1245 /neco/1995/campbell1995neco-target/

Abstract

We propose an efficient procedure for constructing and training a feedforward neural network. The network can perform binary classification for binary or analogue input data. We show that the procedure can also be used to construct feedforward neural networks with binary-valued weights. Neural networks with binary-valued weights are potentially straightforward to implement using microelectronic or optical devices and they can also exhibit good generalization.

NeCo Semantic Scholar

Cite

Text

Campbell and Vicente. "The Target Switch Algorithm: A Constructive Learning Procedure for Feed-Forward Neural Networks." Neural Computation, 1995. doi:10.1162/NECO.1995.7.6.1245

Markdown

[Campbell and Vicente. "The Target Switch Algorithm: A Constructive Learning Procedure for Feed-Forward Neural Networks." Neural Computation, 1995.](https://mlanthology.org/neco/1995/campbell1995neco-target/) doi:10.1162/NECO.1995.7.6.1245

BibTeX

@article{campbell1995neco-target,
  title     = {{The Target Switch Algorithm: A Constructive Learning Procedure for Feed-Forward Neural Networks}},
  author    = {Campbell, Colin and Vicente, Conrado J. Pérez},
  journal   = {Neural Computation},
  year      = {1995},
  pages     = {1245-1264},
  doi       = {10.1162/NECO.1995.7.6.1245},
  volume    = {7},
  url       = {https://mlanthology.org/neco/1995/campbell1995neco-target/}
}