Journal
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, ICAISC 2017, PT I
Volume 10245, Issue -, Pages 97-106Publisher
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-59063-9_9
Keywords
Deep neural networks; Vanishing gradient; Nonlinearity
Categories
Funding
- National Science Centre, Cracow, Poland [2013/11/B/ST6/01337]
Ask authors/readers for more resources
Research in deep neural networks are becoming popular in artificial intelligence. Main reason for training difficulties is the problem of vanishing gradients while number of layers increases. While such networks are very powerful they are difficult in training. The paper discusses capabilities of different neural network architectures and presents the proposition of new multilayer architecture with additional linear neurons, that is much easier to train that traditional MLP network and reduces effect of vanishing gradients. Efficiency of suggested approach has been confirmed by several exeriments.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available