Abstract | ||
---|---|---|
We have developed a small scale four-layered neural network (NN) model for simple character recognition, which can recognize the patterns transformed by affine conversion. It learns by backpropagation to obtain the characteristics of the simple cell and the complex cell in the visual cortex. In this study 24 patterns are presented as input patterns. An input pattern is divided into 64 local patterns and connected with the 1st hidden layer as in the visual cortex. The proposed NN model has good performance of the feature extraction in first layers. |
Year | DOI | Venue |
---|---|---|
2003 | 10.1007/978-3-540-45226-3_111 | LECTURE NOTES IN ARTIFICIAL INTELLIGENCE |
Keywords | Field | DocType |
feature extraction,neural network,backpropagation,neural network model,pattern recognition | Affine transformation,Pattern recognition,Complex cell,Computer science,Simple cell,Feature extraction,Time delay neural network,Feature (machine learning),Artificial intelligence,Artificial neural network,Backpropagation | Conference |
Volume | ISSN | Citations |
2774 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 1 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hirohito Shintani | 1 | 1 | 0.76 |
Hirofumi Nagashino | 2 | 6 | 7.07 |
Akutagawa Masatake | 3 | 13 | 11.43 |
Y. Kinouchi | 4 | 22 | 16.80 |