Presentation 2019-12-20
Estimation of $q$-value of $q$-normal distribution through CNN
Yukito Miyakawa, Ryosuke Hosaka, Masaru Tanaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) It is usually assumed that the given data follow a normal distribution or $t$ distribution for the sake of simplicity.The normal distribution can be assumed by the law of large numbers and the central limit theorem, but the support is non-compact.Because the actual data is in a finite range, the support that the data is supposed to follow does not have to be non-compact.In other words, the support of probability distributions assumed in real data is compact.We focus on the $q$-normal distribution, which is compact and close to the normal distribution.If the value of $q$ can be estimated from the distribution of data, a more appropriate probability distribution can be proposed than the normal distribution.In this paper, we report an experiment to estimate the value of $q$ from the distribution of data through the convolutional neural network.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) $q$-normal distribution / convolutional neural network
Paper # PRMU2019-58
Date of Issue 2019-12-12 (PRMU)

Conference Information
Committee PRMU
Conference Date 2019/12/19(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yoichi Sato(Univ. of Tokyo)
Vice Chair Toru Tamaki(Hiroshima Univ.) / Akisato Kimura(NTT)
Secretary Toru Tamaki(NTT) / Akisato Kimura(OMRON SINICX)
Assistant Yusuke Uchida(DeNA) / Takayoshi Yamashita(Chubu Univ.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Estimation of $q$-value of $q$-normal distribution through CNN
Sub Title (in English)
Keyword(1) $q$-normal distribution
Keyword(2) convolutional neural network
1st Author's Name Yukito Miyakawa
1st Author's Affiliation Fukuoka University(Fukuoka Univ.)
2nd Author's Name Ryosuke Hosaka
2nd Author's Affiliation Fukuoka University(Fukuoka Univ.)
3rd Author's Name Masaru Tanaka
3rd Author's Affiliation Fukuoka University(Fukuoka Univ.)
Date 2019-12-20
Paper # PRMU2019-58
Volume (vol) vol.119
Number (no) PRMU-347
Page pp.pp.75-80(PRMU),
#Pages 6
Date of Issue 2019-12-12 (PRMU)