書誌事項
- タイトル別名
-
- Lexical Acquisition using the Active Nature Based on Saliency
- ケンチョセイ ニ モトズク ロボット ノ ノウドウテキ ゴイ カクトク
この論文をさがす
抄録
Observational studies of human infants tell us that they can successfully acquire lexicon and that the relationship between the meaning and the uttered word can be understood from only one teaching session by a caregiver, even though there are many other possible mappings. This paper proposes a lexical acquisition model that makes use of curiosity to associate visual features of observed objects with the labels that are uttered by a caregiver. A robot changes its attention and learning rate based on the curiosity. In experiments with a humanoid robot, the visual features are represented using self-organizing maps that adaptively represent the shape of the observed objects independent of viewpoint.
収録刊行物
-
- 日本ロボット学会誌
-
日本ロボット学会誌 26 (3), 261-270, 2008
一般社団法人 日本ロボット学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390282679701798272
-
- NII論文ID
- 10021142175
-
- NII書誌ID
- AN00141189
-
- ISSN
- 18847145
- 02891824
-
- NDL書誌ID
- 9474343
-
- 本文言語コード
- ja
-
- データソース種別
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可
