Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks
In this paper, we show that noise injection into inputs in unsupervised learning neural networks does not improve their performance as it does in supervised learning neural networks. Specifically, we show that training noise degrades the classification ability of a sparsely connected version of the...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2012
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/94091 http://hdl.handle.net/10220/8195 |