Title
Training the neocognitron network using design of experiments
Abstract
Neocognitron is a hierarchically structured multi-layer neural network that is recognised for its ability to tolerate scaling and rotational effects of the input patterns. However, there are many parameters that describe the hierarchical multi-layer structure of the network which must be adjusted properly for the network to recognise a set of patterns to allow for their scaling and rotational effects.
Year
DOI
Venue
1995
10.1016/0954-1810(95)95752-R
Artificial Intelligence in Engineering
Keywords
DocType
Volume
design of experiments,hand-writing recognition,neocognitron,neural network,pattern recognition
Journal
9
Issue
ISSN
Citations 
2
0954-1810
4
PageRank 
References 
Authors
0.57
1
2
Name
Order
Citations
PageRank
Ming-Yeong Teo151.00
Siang-Kok Sim2253.93