| Presentation | 2022-06-10 [Invited Talk] Computation and learning based on dual stochasticity of the brain Jun-nosuke Teramae, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Neurons and synapses in the brain are highly stochastic devices. Neurons responsible for signal propagation in the brain continuously generate random spike sequences. Synapses that intermediate spike communication between neurons and are responsible for our memory and learning continue to change their state randomly and spontaneously. However, it remains unclear why they are stochastic. Particularly, how the network that consists of the stochastic devices realizes precise computation and reliable learning remains elusive. In this talk, we provide a theory to answer these questions. We propose a model neural network in which neurons and synapses work synergistically to realize efficient learning as a sampling-based Bayesian inference. We also show that the network exhibits properties consistent with various biological observations. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Cortex / Spontaneous activity / Probabilistic computation / Machine learning / Gibbs sampling |
| Paper # | NLP2022-16,CCS2022-16 |
| Date of Issue | 2022-06-02 (NLP, CCS) |
| Conference Information | |
| Committee | CCS / NLP |
|---|---|
| Conference Date | 2022/6/9(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Megumi Akai(Hokkaido Univ.) / Akio Tsuneda(Kumamoto Univ.) |
| Vice Chair | Masaki Aida(TMU) / Hidehiro Nakano(Tokyo City Univ.) / Hiroyuki Torikai(Hosei Univ.) |
| Secretary | Masaki Aida(TDK) / Hidehiro Nakano(Shibaura Insti. of Tech.) / Hiroyuki Torikai(Sojo Univ.) |
| Assistant | Tomoyuki Sasaki(Shonan Instit. of Tech.) / Hiroyasu Ando(Tsukuba Univ.) / Miki Kobayashi(Rissho Univ.) / " Hiroyuki YASUDA(The Univ. of Tokyo) / Yuichi Yokoi(Nagasaki Univ.) / Yoshikazu Yamanaka(Utsunomiya Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Complex Communication Sciences / Technical Committee on Nonlinear Problems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | [Invited Talk] Computation and learning based on dual stochasticity of the brain |
| Sub Title (in English) | |
| Keyword(1) | Cortex |
| Keyword(2) | Spontaneous activity |
| Keyword(3) | Probabilistic computation |
| Keyword(4) | Machine learning |
| Keyword(5) | Gibbs sampling |
| 1st Author's Name | Jun-nosuke Teramae |
| 1st Author's Affiliation | Kyoto University(Kyoto Univ.) |
| Date | 2022-06-10 |
| Paper # | NLP2022-16,CCS2022-16 |
| Volume (vol) | vol.122 |
| Number (no) | NLP-65,CCS-66 |
| Page | pp.pp.78-83(NLP), pp.78-83(CCS), |
| #Pages | 6 |
| Date of Issue | 2022-06-02 (NLP, CCS) |