Presentation 2018-01-26
Infant vocabulary acquisition model using neural networks and reinforcement learning
Akira Noguchi, Yasuhiro Minami,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In early infant vocabulary acquisition, we have caught its characteristics by using various prior knowledge of bias until now. Artificial intelligence calls this events of vocabulary acquisition as symbol grounding of words and concepts. In this research, we propose a method to model the conceptual symbol grounding by abstraction of knowledge using neural network and learning sequence information using reinforcement learning without prior knowledge such as bias. By this method, it was possible to show that prior knowledge such as shape bias can be acquired by learning. It was also possible to show that joint gaze by parents and parents is important as a trigger for vocabulary learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / reinforcement learning / vocabulary acquisition
Paper # HCS2017-76
Date of Issue 2018-01-19 (HCS)

Conference Information
Committee HCS
Conference Date 2018/1/26(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Daiichi Institute of Technology
Topics (in Japanese) (See Japanese page)
Topics (in English) Psychology and Life-stage of Communication, etc.
Chair Yukiko Nakano(Seikei Univ.)
Vice Chair Nobuyuki Watanabe(Kanazawa Inst. of Tech.) / Tomoo Inoue(Univ. of Tsukuba)
Secretary Nobuyuki Watanabe(Ritsumeikan Univ.) / Tomoo Inoue(Osaka Electro-Comm. Univ.)
Assistant Kazuki Takashima(Tohoku Univ.) / Ken Fujiwara(Osaka Univ. of Economic) / Kazunori Terada(Gifu Univ.) / Atsushi Kimura(Nihon Univ.)

Paper Information
Registration To Technical Committee on Human Communication Science
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Infant vocabulary acquisition model using neural networks and reinforcement learning
Sub Title (in English)
Keyword(1) neural network
Keyword(2) reinforcement learning
Keyword(3) vocabulary acquisition
1st Author's Name Akira Noguchi
1st Author's Affiliation University of Electro Communications(UEC)
2nd Author's Name Yasuhiro Minami
2nd Author's Affiliation University of Electro Communications(UEC)
Date 2018-01-26
Paper # HCS2017-76
Volume (vol) vol.117
Number (no) HCS-420
Page pp.pp.59-64(HCS),
#Pages 6
Date of Issue 2018-01-19 (HCS)