Presentation | 2021-11-26 Explaining coarse visual processing in the subcortical pathway with convolutional neural networks Chanseok Lim, Mikio Inagaki, Takashi Shinozaki, Ichiro Fujita, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | The subcortical pathway for face processing conveys information rapidly but roughly to the amygdala. The fast processing arises from the small number of processing stages. However, it is unclear whether the shallowness of processing stages renders the transmitted information coarse. To address this question, we developed a convolutional neural network model with a shallow architecture (SNN), receptive fields similar to those in the first stage of the subcortical pathway, and a greater degree of spatial pooling. The SNN successfully learned to discriminate facial expressions. Units in the final stage represented spatial frequency in the retina-based reference frame in a similar way to the representation in the subcortical pathway. We further compared the SNN model and three modified models in which the three features of the SNN were replaced one by one with the corresponding features in the cortical pathway. The comparison revealed that the coarse representation results not only from the processing shallowness but from the receptive field organization and the degree of spatial pooling. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Vision / Convolutional Neural Network / Subcortical Pathway / Amygdala / Spatial Frequency / Face Recognition |
Paper # | NC2021-28 |
Date of Issue | 2021-11-19 (NC) |
Conference Information | |
Committee | NC / MBE |
---|---|
Conference Date | 2021/11/26(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Rieko Osu(Waseda Univ.) / Ryuhei Okuno(Setsunan Univ.) |
Vice Chair | Hiroshi Yamakawa(Univ of Tokyo) / Junichi Hori(Niigata Univ.) |
Secretary | Hiroshi Yamakawa(ATR) / Junichi Hori(NICT) |
Assistant | Nobuhiko Wagatsuma(Toho Univ.) / Tomoki Kurikawa(KMU) / Jun Akazawa(Meiji Univ. of Integrative Medicine) / Emi Yuda(Tohoku Univ) |
Paper Information | |
Registration To | Technical Committee on Neurocomputing / Technical Committee on ME and Bio Cybernetics |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Explaining coarse visual processing in the subcortical pathway with convolutional neural networks |
Sub Title (in English) | |
Keyword(1) | Vision |
Keyword(2) | Convolutional Neural Network |
Keyword(3) | Subcortical Pathway |
Keyword(4) | Amygdala |
Keyword(5) | Spatial Frequency |
Keyword(6) | Face Recognition |
1st Author's Name | Chanseok Lim |
1st Author's Affiliation | Osaka University(Osaka Univ.) |
2nd Author's Name | Mikio Inagaki |
2nd Author's Affiliation | Osaka University(Osaka Univ.) |
3rd Author's Name | Takashi Shinozaki |
3rd Author's Affiliation | National Institute of Information and Communications Technology(NICT) |
4th Author's Name | Ichiro Fujita |
4th Author's Affiliation | Osaka University(Osaka Univ.) |
Date | 2021-11-26 |
Paper # | NC2021-28 |
Volume (vol) | vol.121 |
Number (no) | NC-271 |
Page | pp.pp.1-6(NC), |
#Pages | 6 |
Date of Issue | 2021-11-19 (NC) |