16 December 1992 Modified Hebbian learning for large object classes using Neocognitron visual recognition
Author Affiliations +
Abstract
Hebbian learning law plays a very important role in the feedforward learning of neural networks. In multidimensional image space, particularly in vision, the asymmetric multidimensional Hebbian learning law can perform principal component feature extraction, thus providing high dimensional feature analysis and feature separation. In this paper, we verified this principle with modified Hebbian learning when applied to Fukushima's neocognitron visual recognition architecture.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Thomas Y. P. Lee, Thomas Y. P. Lee, Clark C. Guest, Clark C. Guest, } "Modified Hebbian learning for large object classes using Neocognitron visual recognition", Proc. SPIE 1766, Neural and Stochastic Methods in Image and Signal Processing, (16 December 1992); doi: 10.1117/12.130822; https://doi.org/10.1117/12.130822
PROCEEDINGS
12 PAGES


SHARE
Back to Top