Title :
Multilayer recurrent neural networks [character recognition application example]
Author_Institution :
Dept. of Electr. & Comput. Eng., Windsor Univ., Ont., Canada
Abstract :
In this paper, multilayer recurrent neural networks in the form of 3-layer bidirectional symmetrical and asymmetrical associative memories are presented. The networks possess the features of both a multilayer feedforward neural network and a bidirectional associative memory. These networks can have two modes of recalling; namely, recalling by one pattern and recalling by a pattern pair. Simulation results on alpha numeral type pattern recognition performance under noisy conditions are given.
Keywords :
character recognition; content-addressable storage; feedforward neural nets; recurrent neural nets; alpha numeral pattern recognition; asymmetrical associative memories; bidirectional associative memory; bidirectional symmetrical associative memories; character recognition; multilayer feedforward neural network; multilayer recurrent neural networks; noisy image conditions; pattern pair recall; recall modes; single pattern recalling; Associative memory; Backpropagation algorithms; Feedforward neural networks; Hebbian theory; Magnesium compounds; Multi-layer neural network; Neural networks; Neurons; Pattern recognition; Recurrent neural networks;
Conference_Titel :
Circuits and Systems, 2002. MWSCAS-2002. The 2002 45th Midwest Symposium on
Print_ISBN :
0-7803-7523-8
DOI :
10.1109/MWSCAS.2002.1186979
