Please use this identifier to cite or link to this item:
Title: GA-based supervised learning of neocognitron
Authors: Shi, Daming 
Tan, Chew Lira 
Issue Date: 2000
Citation: Shi, Daming,Tan, Chew Lira (2000). GA-based supervised learning of neocognitron. Proceedings of the International Joint Conference on Neural Networks 6 : 559-564. ScholarBank@NUS Repository.
Abstract: Supervised learning of Neocognitron is fulfilled by presenting the training patterns, which are mapping to specified features respectively. However, the training patterns and many parameters are designed empirically and set manually in Fukushima's Neocognitron. In this paper, we use Genetic Algorithms (GAs) to tune the parameters of Neocognitron and search its reasonable training pattern sets. First of all, the correlation amongst the training patterns is considered as a critical factor affecting Neocognitron's performance, but it is ignored in the design of the original Neocognitron. And then, a GA-based supervised learning of the Neocognitron is proposed to tune the parameters and search training patterns. The results prove that the performance of a Neocognition is sensitive to its training patterns, selectivity and receptive fields, and can be improved by this supervised learning on the basis of GAs and the correlation analysis.
Source Title: Proceedings of the International Joint Conference on Neural Networks
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.