Incremental learning in autonomous systems: evolving connectionist systems for on-line image and speech recognition

Author

Kasabov, Nikola ; Zhang, David ; Pang, P.S.

Author_Institution

Inst. of Knowledge Eng. & Discovery Res., Auckland Univ. of Technol., New Zealand

fYear

2005

fDate

12-15 June 2005

Firstpage

120

Lastpage

125

Abstract

The paper presents an integrated approach to incremental learning in autonomous systems, that includes both pattern recognition and feature selection. The approach utilizes evolving connectionist systems (ECoS) and is applied on on-line image and speech pattern learning and recognition tasks. The experiments show that ECoS are a suitable paradigm for building autonomous systems for learning and navigation in a new environment using both image and speech modalities.

Keywords

feature extraction; image recognition; learning (artificial intelligence); speech recognition; adaptive systems; autonomous systems; evolving connectionist systems; evolving growing cluster classifier; feature selection; incremental learning; multimodal systems; online image recognition; online speech recognition; speech pattern learning; Carbon capture and storage; Clustering algorithms; Computational intelligence; Image recognition; Intelligent robots; Knowledge engineering; Neural networks; Pattern recognition; Speech recognition; Streaming media;

fLanguage

English

Publisher

ieee

Conference_Titel

Advanced Robotics and its Social Impacts, 2005. IEEE Workshop on

Print_ISBN

0-7803-8947-6

Type

conf

DOI

10.1109/ARSO.2005.1511636

Filename

1511636