A fast training algorithm is developed for two-layer feedforward neural networks based on a probabilistic model for hidden representations and the EM algorithm. The algorithm decomposes training the original two-layer networks into training a set of single neurons. The individual neurons are then trained via a linear weighted regression algorithm. Significant improvement on training speed has been made using this algorithm for several bench-mark problems. Copyright 1997 Elsevier Science Ltd. All Rights Reserved.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/s0893-6080(96)00049-4 | DOI Listing |
Publication Analysis
Top Keywords
training algorithm
8
feedforward neural
8
neural networks
8
algorithm
6
training
5
efficient em-based
4
em-based training
4
algorithm feedforward
4
networks fast
4
fast training
4
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!