| Presentation | 2020-10-21 ［招待講演］確率的生成モデルによる記号創発システムの表現 , |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A symbol emergence system is a multi-agent system where each autonomous agent forms internal representations through interactions with its environment and communicate with other agents using signs. The meanings of the signs are not designed in a top-down manner but should be formed in a bottom-up manner. It is widely accepted that the meanings of signs are arbitrarily determined in a community or a society. The mathematical models for representing the dynamics of symbol emergence systems has not been fully explored. The talk introduces a constructive model of a symbol emergence system in which two robots are regarded as a part of the probabilistic generative model. It models the total dynamics of the symbol emergence system, and the bottom-up formation of symbolic systems is regarded as the inference process of the latent variable shared among the robots. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Probabilistic generative model / Symbol emergence systems / language evolution / Symbol emergence in robotics / representation learning / multimodal categorization |
| Paper # | IBISML2020-18 |
| Date of Issue | 2020-10-13 (IBISML) |
| Conference Information | |
| Committee | IBISML |
|---|---|
| Conference Date | 2020/10/20(3days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Online |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Organized Sessions on Frontiers of Machine Learning and General Sessions |
| Chair | Ichiro Takeuchi(Nagoya Inst. of Tech.) |
| Vice Chair | Masashi Sugiyama(Univ. of Tokyo) / Koji Tsuda(Univ. of Tokyo) |
| Secretary | Masashi Sugiyama(AIST) / Koji Tsuda(NTT) |
| Assistant | Atsuyoshi Nakamura(Hokkaido Univ.) / Shigeyuki Oba(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Infomation-Based Induction Sciences and Machine Learning |
|---|---|
| Language | JPN-ONLY |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | |
| Sub Title (in English) | |
| Keyword(1) | Probabilistic generative model |
| Keyword(2) | Symbol emergence systems |
| Keyword(3) | language evolution |
| Keyword(4) | Symbol emergence in robotics |
| Keyword(5) | representation learning |
| Keyword(6) | multimodal categorization |
| 1st Author's Name | |
| 1st Author's Affiliation | *(*) |
| Date | 2020-10-21 |
| Paper # | IBISML2020-18 |
| Volume (vol) | vol.120 |
| Number (no) | IBISML-195 |
| Page | pp.pp.34-35(IBISML), |
| #Pages | 2 |
| Date of Issue | 2020-10-13 (IBISML) |