Parameterless-Growing-SOM and Its Application to a Voice Instruction Learning System
Joint Authors
Komoto, Takahito
Obayashi, Masanao
Kobayashi, Kunikazu
Kuremoto, Takashi
Source
Issue
Vol. 2010, Issue 2010 (31 Dec. 2010), pp.1-9, 9 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2010-08-17
Country of Publication
Egypt
No. of Pages
9
Main Subjects
Abstract EN
An improved self-organizing map (SOM), parameterless-growing-SOM (PL-G-SOM), is proposed in this paper.
To overcome problems existed in traditional SOM (Kohonen, 1982), kinds of structure-growing-SOMs or parameter-adjusting-SOMs have been invented and usually separately.
Here, we combine the idea of growing SOMs (Bauer and Villmann, 1997; Dittenbach et al.
2000) and a parameterless SOM (Berglund and Sitte, 2006) together to be a novel SOM named PL-G-SOM to realize additional learning, optimal neighborhood preservation, and automatic tuning of parameters.
The improved SOM is applied to construct a voice instruction learning system for partner robots adopting a simple reinforcement learning algorithm.
User's instructions of voices are classified by the PL-G-SOM at first, then robots choose an expected action according to a stochastic policy.
The policy is adjusted by the reward/punishment given by the user of the robot.
A feeling map is also designed to express learning degrees of voice instructions.
Learning and additional learning experiments used instructions in multiple languages including Japanese, English, Chinese, and Malaysian confirmed the effectiveness of our proposed system.
American Psychological Association (APA)
Kuremoto, Takashi& Komoto, Takahito& Kobayashi, Kunikazu& Obayashi, Masanao. 2010. Parameterless-Growing-SOM and Its Application to a Voice Instruction Learning System. Journal of Robotics،Vol. 2010, no. 2010, pp.1-9.
https://search.emarefa.net/detail/BIM-462143
Modern Language Association (MLA)
Kuremoto, Takashi…[et al.]. Parameterless-Growing-SOM and Its Application to a Voice Instruction Learning System. Journal of Robotics No. 2010 (2010), pp.1-9.
https://search.emarefa.net/detail/BIM-462143
American Medical Association (AMA)
Kuremoto, Takashi& Komoto, Takahito& Kobayashi, Kunikazu& Obayashi, Masanao. Parameterless-Growing-SOM and Its Application to a Voice Instruction Learning System. Journal of Robotics. 2010. Vol. 2010, no. 2010, pp.1-9.
https://search.emarefa.net/detail/BIM-462143
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-462143