2000年
Self-reflective learning of invariants in human-artifact interactions using recurrent neural network
IECON 2000: 26TH ANNUAL CONFERENCE OF THE IEEE INDUSTRIAL ELECTRONICS SOCIETY, VOLS 1-4
- ,
- 巻
- 4
- 号
- 開始ページ
- 2595
- 終了ページ
- 2601
- 記述言語
- 英語
- 掲載種別
- DOI
- 10.1109/IECON.2000.972407
- 出版者・発行元
- IEEE
Human bodily motions are effectively used to communicate, and the ability to read the intentions behind those is essentially important for the machine system to collaborate with the human. If we use. behaviors as medium of communication with the machine, the machine system should be able to construct meanings from them. In this paper. semiosis and related topics of symbol grounding are reviewed, and motion understanding is discussed in terms of that framework. Then. a method for extracting meanings from a series of human bodily motion is presented using a recurrent neural not-work (RNN). Finally we discuss about what the RNN learning implies with respect to semiosis.
- リンク情報
- ID情報
-
- DOI : 10.1109/IECON.2000.972407
- ISSN : 1553-572X
- Web of Science ID : WOS:000176916400440