A Concept Generation Method Based on Mutual Information Quantity among Multiple Self-organizing Maps

Authors:
Kunio Kitahara;Akira Hirose
Affiliations:
Department of Electronic Engineering, The University of Tokyo, Tokyo, Japan 113-8656;Department of Electronic Engineering, The University of Tokyo, Tokyo, Japan 113-8656
Venue:
ICONIP '09 Proceedings of the 16th International Conference on Neural Information Processing: Part II
Year:
2009

Citing 4
Cited 1

Self-organized formation of various invariant-feature filters in the adaptive-subspace SOM

Neural Computation
ELIZA—a computer program for the study of natural language communication between man and machine

Communications of the ACM
Understanding Computers and Cognition: A New Foundation for Design

Understanding Computers and Cognition: A New Foundation for Design
Robots that learn language: developmental approach to human-machine conversations

EELC'06 Proceedings of the Third international conference on Emergence and Evolution of Linguistic Communication: symbol Grounding and Beyond

Ground penetrating radar system with integration of mutimodal information based on mutual information among multiple self-organizing maps

ICONIP'10 Proceedings of the 17th international conference on Neural information processing: models and applications - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

We propose a concept generation method based on mutual information smong multiple self-organizing maps. There have been many reports on concept generation in various fields such as linguistics and robotics. In the context of language acquisition, however, they mainly deal with letters, i.e. symbols, in general. Since both the concept and language acquisitions progress in parallel, we notice the importance to investigate concept generation without symbols existing a priori. In this paper, we propose a non-symbol-based method that pays attention to multimodal mutual information.