Presentation | 2011-03-11 Adaptive Learning of Activation Function of Layer Neural Network Daisuke SEI, Masahiro NAKAMURA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, on back propagation of a layer neural network, we study the effect of adaptive learning of activation function not only weight and levels. We prepare two of non-liner separation problem, and get the learning success rate and mean the number of learning times by searching the number of times on mean squared error (MSE) under the constant value and the number of learning times. The result is that we confirmed adaptive learning is faster than normal one. So we confirmed that adaptive learning is effective for acceleration of learning. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Layer Neural Network / Back Propagation |
Paper # | NLP2010-191 |
Date of Issue |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 2011/3/3(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Nonlinear Problems (NLP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Adaptive Learning of Activation Function of Layer Neural Network |
Sub Title (in English) | |
Keyword(1) | Layer Neural Network |
Keyword(2) | Back Propagation |
1st Author's Name | Daisuke SEI |
1st Author's Affiliation | Nagaoka University of Techonology() |
2nd Author's Name | Masahiro NAKAMURA |
2nd Author's Affiliation | Nagaoka University of Techonology |
Date | 2011-03-11 |
Paper # | NLP2010-191 |
Volume (vol) | vol.110 |
Number (no) | 465 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |