ML Anthology

Backpropagation with Homotopy

Liping Yang, Wanzhen Yu
NeCo 1993 pp. 363-366
doi:10.1162/NECO.1993.5.3.363 /neco/1993/yang1993neco-backpropagation/

Abstract

When training a feedforward neural network with backpropagation (Rumelhart et al. 1986), local minima are always a problem because of the nonlinearity of the system. There have been several ways to attack this problem: for example, to restart the training by selecting a new initial point, to perform the preprocessing of the input data or the neural network. Here, we propose a method which is efficient in computation to avoid some local minima.

NeCo Semantic Scholar

Cite

Text

Yang and Yu. "Backpropagation with Homotopy." Neural Computation, 1993. doi:10.1162/NECO.1993.5.3.363

Markdown

[Yang and Yu. "Backpropagation with Homotopy." Neural Computation, 1993.](https://mlanthology.org/neco/1993/yang1993neco-backpropagation/) doi:10.1162/NECO.1993.5.3.363

BibTeX

@article{yang1993neco-backpropagation,
  title     = {{Backpropagation with Homotopy}},
  author    = {Yang, Liping and Yu, Wanzhen},
  journal   = {Neural Computation},
  year      = {1993},
  pages     = {363-366},
  doi       = {10.1162/NECO.1993.5.3.363},
  volume    = {5},
  url       = {https://mlanthology.org/neco/1993/yang1993neco-backpropagation/}
}