Presentation information

General Session

General Session » [GS] J-11 Robot and real worlds

[1L4-J-11] Robot and real worlds: learning of robots

Tue. Jun 4, 2019 5:20 PM - 6:40 PM Room L (203+204 Small meeting rooms)

Chair:Yoshimasa Tawatsuji Reviewer:Masakazu Hirokawa

6:20 PM - 6:40 PM

[1L4-J-11-04] Simultaneous Learning of Object Concepts, Language Model, and Acoustic Model Using Unsupervised Multimodal Learning

〇Hiroaki Murakami1, Ryo Ozaki1, Akira Taniguchi1, Tadahiro Taniguchi1 (1. Ritsumeikan University)

Keywords:unsupervised learning, object concept, simultaneous learning

Categorization of objects plays an important role in human cognition. It is important for robots to form the object concepts for communication with humans. The purpose is to enable that robots form such object categories and acquire language. We propose the simultaneous learning of the object concepts, the language model, and the acoustic model using by combining Multimodal Latent Dirichlet Allocation (MLDA) with Nonparametric Bayesian Double Articulation Analyzer (NPB-DAA).