Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Backpropagation with Homotopy

Backpropagation with Homotopy 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. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Neural Computation MIT Press

Backpropagation with Homotopy

Neural Computation , Volume 5 (3) – May 1, 1993

Loading next page...
 
/lp/mit-press/backpropagation-with-homotopy-Us8doTGWDd

References (5)

Publisher
MIT Press
Copyright
© 1993 Massachusetts Institute of Technology
ISSN
0899-7667
eISSN
1530-888X
DOI
10.1162/neco.1993.5.3.363
Publisher site
See Article on Publisher Site

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.

Journal

Neural ComputationMIT Press

Published: May 1, 1993

There are no references for this article.