Noise injection into inputs in sparsely connected Hopfield and winner-take-all neural networks

• 主要作者: Wang, Lipo.
• 其他作者: School of Electrical and Electronic Engineering
• 格式: Article
• 語言: English
• 出版: 2012
• 主題: DRNTU::Engineering::Electrical and electronic engineering
• 在線閱讀: https://hdl.handle.net/10356/94091; http://hdl.handle.net/10220/8195
• 機構: Nanyang Technological University

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...