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...
Saved in:
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: | |
在線閱讀: | https://hdl.handle.net/10356/94091 http://hdl.handle.net/10220/8195 |
標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
相似書籍
-
Winner-takes-all mechanism realized by memristive neural network
由: Wang, Jun Jie, et al.
出版: (2020) -
Advantages of direct input-to-output connections in neural networks : the Elman network for stock index forecasting
由: Wang, Yaoli, et al.
出版: (2021) -
Study of recall time of associative memory in a memristive Hopfield neural network
由: Kong, Deyu, et al.
出版: (2019) -
Image reconstruction by a Hopfield neural network
由: Srinivasan, V., et al.
出版: (2014) -
An efficient dilated convolutional neural network for UAV noise reduction at low input SNR
由: Tan, Zhi-Wei, et al.
出版: (2020)