Effect of Additive Noise for Multi-Layered Perceptron with AutoEncoders
-
- SABRI Motaz
- Hiroshima University
-
- KURITA Takio
- Hiroshima University
Abstract
<p>This paper investigates the effect of noises added to hidden units of AutoEncoders linked to multilayer perceptrons. It is shown that internal representation of learned features emerges and sparsity of hidden units increases when independent Gaussian noises are added to inputs of hidden units during the deep network training. It is also shown that the weights that connect the contaminated hidden units with the next layer have smaller values and outputs of hidden units tend to be more definite (0 or 1). This is expected to improve the generalization ability of the network through this automatic structuration by adding the noises. This network structuration was confirmed by experiments for MNIST digits classification via a deep neural network model.</p>
Journal
-
- IEICE Transactions on Information and Systems
-
IEICE Transactions on Information and Systems E100.D (7), 1494-1504, 2017
The Institute of Electronics, Information and Communication Engineers
- Tweet
Details
-
- CRID
- 1390001204378097536
-
- NII Article ID
- 130006792948
-
- ISSN
- 17451361
- 09168532
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- KAKEN
-
- Abstract License Flag
- Disallowed