Presentation | 2017-06-23 Analysis of Robustness of Approximators Based on Neural Networks Against Redundant Dimensions Shoichi Someno, Tomohiro Tanno, Kazumasa Horie, Jun Izawa, Tomoki Ichiba, Masahiko Morita, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Redundant input dimensions that are not related to the output are known to lower the approximate accuracy of function approximators, but it is unclear which approximator is especially sensitive or robust to them. The present study compared the robustness of several neural network based approximators against redundant dimensions through numerical experiments on several simple fuinction approximation tasks. As a result, the approximator based on the method of pattern coding and the network of parallel perceptron was robust not only to redundant dimensions but also to partly-redundant dimensions that are not completely redundant but partly relevant to the output. Furthermore, the results implied that this approximator may be able to contribute to specify which input dimensions are redundant. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Function approximation / Neural network / Redundant dimension / Pattern coding / Parallel perceptron |
Paper # | NC2017-8 |
Date of Issue | 2017-06-16 (NC) |
Conference Information | |
Committee | NC / IPSJ-BIO / IBISML / IPSJ-MPS |
---|---|
Conference Date | 2017/6/23(3days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Okinawa Institute of Science and Technology |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Machine Learning Approach to Biodata Mining, and General |
Chair | Masafumi Hagiwara(Keio Univ.) / / Kenji Fukumizu(ISM) |
Vice Chair | Yutaka Hirata(Chubu Univ.) / / Masashi Sugiyama(Univ. of Tokyo) |
Secretary | Yutaka Hirata(Tokyo Inst. of Tech.) / (Nagoya Univ.) / Masashi Sugiyama / (Kyoto Univ.) |
Assistant | Yoshihisa Shinozawa(Keio Univ.) / Keiichiro Inagaki(Chubu Univ.) / / Ichiro Takeuchi(Nagoya Inst. of Tech.) / Toshihiro Kamishima(AIST) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Special Interest Group on Bioinformatics and Genomics / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Mathematical Modeling and Problem Solving |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Analysis of Robustness of Approximators Based on Neural Networks Against Redundant Dimensions |
Sub Title (in English) | |
Keyword(1) | Function approximation |
Keyword(2) | Neural network |
Keyword(3) | Redundant dimension |
Keyword(4) | Pattern coding |
Keyword(5) | Parallel perceptron |
1st Author's Name | Shoichi Someno |
1st Author's Affiliation | Tsukuba University(Tsukuba Univ.) |
2nd Author's Name | Tomohiro Tanno |
2nd Author's Affiliation | Tsukuba University(Tsukuba Univ.) |
3rd Author's Name | Kazumasa Horie |
3rd Author's Affiliation | Tsukuba University(Tsukuba Univ.) |
4th Author's Name | Jun Izawa |
4th Author's Affiliation | Tsukuba University(Tsukuba Univ.) |
5th Author's Name | Tomoki Ichiba |
5th Author's Affiliation | Tsukuba University(Tsukuba Univ.) |
6th Author's Name | Masahiko Morita |
6th Author's Affiliation | Tsukuba University(Tsukuba Univ.) |
Date | 2017-06-23 |
Paper # | NC2017-8 |
Volume (vol) | vol.117 |
Number (no) | NC-109 |
Page | pp.pp.21-26(NC), |
#Pages | 6 |
Date of Issue | 2017-06-16 (NC) |