Share Email Print
cover

Proceedings Paper

Autonomous mental development with selective attention, object perception, and knowledge representation
Author(s): Sang-Woo Ban; Minho Lee
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Knowledge-based clustering and autonomous mental development remains a high priority research topic, among which the learning techniques of neural networks are used to achieve optimal performance. In this paper, we present a new framework that can automatically generate a relevance map from sensory data that can represent knowledge regarding objects and infer new knowledge about novel objects. The proposed model is based on understating of the visual what pathway in our brain. A stereo saliency map model can selectively decide salient object areas by additionally considering local symmetry feature. The incremental object perception model makes clusters for the construction of an ontology map in the color and form domains in order to perceive an arbitrary object, which is implemented by the growing fuzzy topology adaptive resonant theory (GFTART) network. Log-polar transformed color and form features for a selected object are used as inputs of the GFTART. The clustered information is relevant to describe specific objects, and the proposed model can automatically infer an unknown object by using the learned information. Experimental results with real data have demonstrated the validity of this approach.

Paper Details

Date Published: 3 April 2008
PDF: 12 pages
Proc. SPIE 6979, Independent Component Analyses, Wavelets, Unsupervised Nano-Biomimetic Sensors, and Neural Networks VI, 69790Q (3 April 2008); doi: 10.1117/12.791742
Show Author Affiliations
Sang-Woo Ban, Dongguk Univ. (South Korea)
Minho Lee, Kyungpook National Univ. (South Korea)


Published in SPIE Proceedings Vol. 6979:
Independent Component Analyses, Wavelets, Unsupervised Nano-Biomimetic Sensors, and Neural Networks VI
Harold H. Szu; F. Jack Agee, Editor(s)

© SPIE. Terms of Use
Back to Top