IEICE Transactions on Information and Systems
Online ISSN : 1745-1361
Print ISSN : 0916-8532
Regular Section
Effect of Additive Noise for Multi-Layered Perceptron with AutoEncoders
Motaz SABRITakio KURITA
Author information
JOURNAL FREE ACCESS

2017 Volume E100.D Issue 7 Pages 1494-1504

Details
Abstract

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.

Content from these authors
© 2017 The Institute of Electronics, Information and Communication Engineers
Previous article Next article
feedback
Top