Abstract
Quickprop is one of the most popular fast learning algorithms in training feed-forward neural networks. Its learning rate is fast; however, it is still limited by the gradient of the backpropagation algorithm and it is easily trapped into a local minimum. Proposed is a new fast learning algorithm to overcome these two drawbacks. The performance investigation in different learning problems (applications) shows that the new algorithm always converges with a faster learning rate compared with Quickprop and other fast learning algorithms. The improvement in global convergence capability is especially large, which increased from 4 to 100 in one learning problem.
Original language | English |
---|---|
Pages (from-to) | 678-679 |
Number of pages | 2 |
Journal | Electronics Letters |
Volume | 48 |
Issue number | 12 |
DOIs | |
Publication status | Published - 7 Jun 2012 |
ASJC Scopus subject areas
- Electrical and Electronic Engineering