| Presentation | 2018-12-06 What is the ethics of the inverse reinforcement learning system that circulates probability measure texts and deterministic texts Tetsuya Morizumi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In the Internet, the system is designed and operated by a logic viewpoint based on determinism. If you design the system deterministically, its safety, integrity and soundness can be easily proved, that is, it is easy to design. However, systems designed with determinism force to bind humans by rule. Now, the system which lacks the viewpoint of continues uncritically developing, and as its ultimate appearance artificial intelligence appears while raising various problems. What kind of approach should we approach to incorporate the viewpoint of into an artificial intelligent system? In this paper I present the following conceptual design: "To positively incorporate the viewpoint of others into artificial intelligence", at the same time "aim to be a system that can change the rules themselves from the viewpoint of while adhering to deterministic rules". In other words, I design the concept of Wittgenstein's language-game and the concept of “Riken-no-ken (sight outside of sight)” used in Ze’ami’s treatise on Noh as a machine learning system against the question "How each interpret others". In the machine learning mechanism, combine supervised learning and unsupervised learning, and apply reverse reinforcement learning to Bayesian updating of teacher data. This system realizes "a system to reverse reinforcement learning from the viewpoint of other people's intention". Then I will try ethical consideration on this system. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | artificial intelligence / determinism / stochastic model / inverse reinforcement learning / Wittgenstein / Language-game / Ze’ami / ethics |
| Paper # | SITE2018-62 |
| Date of Issue | 2018-11-29 (SITE) |
| Conference Information | |
| Committee | SITE |
|---|---|
| Conference Date | 2018/12/6(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Tetsuya Morizumi(Kanagawa Univ.) |
| Vice Chair | Masaru Ogawa(Kobe Gakuin Univ.) / Takushi Otani(Kibi International Univ.) |
| Secretary | Masaru Ogawa(Tokyo Health Care Univ.) / Takushi Otani(Toyo Eiwa Univ.) |
| Assistant | Hisanori Kato(KDDI Research) / Nobuyuki Yoshinaga(Yamaguchi Pref Univ.) / Daisuke Suzuki(Hokuriku Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Social Implications of Technology and Information Ethics |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | What is the ethics of the inverse reinforcement learning system that circulates probability measure texts and deterministic texts |
| Sub Title (in English) | |
| Keyword(1) | artificial intelligence |
| Keyword(2) | determinism |
| Keyword(3) | stochastic model |
| Keyword(4) | inverse reinforcement learning |
| Keyword(5) | Wittgenstein |
| Keyword(6) | Language-game |
| Keyword(7) | Ze’ami |
| Keyword(8) | ethics |
| 1st Author's Name | Tetsuya Morizumi |
| 1st Author's Affiliation | Kanagawa University(KU) |
| Date | 2018-12-06 |
| Paper # | SITE2018-62 |
| Volume (vol) | vol.118 |
| Number (no) | SITE-345 |
| Page | pp.pp.17-23(SITE), |
| #Pages | 7 |
| Date of Issue | 2018-11-29 (SITE) |