Presentation | 2018-01-18 Convolutional Neural Network based on Entanglement Entropy and Convolutional Neural Network based on Principal Component Analysis Shu Eggchee, Masaru Tanaka, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we study the differences in the CNN performing processing in accordance with the data using the CNN and entanglement entropy for performing processing in accordance with the data using the principal component analysis. CNN performing processing in accordance with the data using the entanglement entropy eliminates pooling and dropouts used in general CNN, proper selection of unnecessary information for each data based on entanglement entropy Based on the amount of information to be learned. Specifically, unnecessary information reduction using singular value decomposition based on entanglement and entropy is performed. On the other hand, in the field of image processing, image compression using singular value decomposition is often performed based on the contribution ratio of principal component analysis. CNN performing processing in accordance with the data using the principal component analysis is a learning method using about contraction of dimensions based on the contribution rate of principal component analysis of the original data. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | quantum mechanics / entanglement entropy / principal component analysis / singular value decomposition / convolutional neural network |
Paper # | PRMU2017-129,MVE2017-50 |
Date of Issue | 2018-01-11 (PRMU, MVE) |
Conference Information | |
Committee | PRMU / MVE / IPSJ-CVIM |
---|---|
Conference Date | 2018/1/18(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Shinichi Sato(NII) / Yoshinari Kameda(Univ. of Tsukuba) |
Vice Chair | Hironobu Fujiyoshi(Chubu Univ.) / Yoshihisa Ijiri(Omron) / Kenji Mase(Nagoya Univ.) |
Secretary | Hironobu Fujiyoshi(AIST) / Yoshihisa Ijiri(NAIST) / Kenji Mase(Kyoto Univ.) / (NTT) |
Assistant | Masato Ishii(NEC) / Yusuke Sugano(Osaka Univ.) / Takatsugu Hirayama(Nagoya Univ.) / Ryosuke Aoki(NTT) |
Paper Information | |
Registration To | Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Media Experience and Virtual Environment / Special Interest Group on Computer Vision and Image Media |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Convolutional Neural Network based on Entanglement Entropy and Convolutional Neural Network based on Principal Component Analysis |
Sub Title (in English) | |
Keyword(1) | quantum mechanics |
Keyword(2) | entanglement entropy |
Keyword(3) | principal component analysis |
Keyword(4) | singular value decomposition |
Keyword(5) | convolutional neural network |
1st Author's Name | Shu Eggchee |
1st Author's Affiliation | Fukuoka University(Fukuoka Univ.) |
2nd Author's Name | Masaru Tanaka |
2nd Author's Affiliation | Fukuoka University(Fukuoka Univ.) |
Date | 2018-01-18 |
Paper # | PRMU2017-129,MVE2017-50 |
Volume (vol) | vol.117 |
Number (no) | PRMU-391,MVE-392 |
Page | pp.pp.141-146(PRMU), pp.141-146(MVE), |
#Pages | 6 |
Date of Issue | 2018-01-11 (PRMU, MVE) |