Title :
Three-layer symmetrical and asymmetrical associative memories for image applications
Author_Institution :
Dept. of Electr. & Comput. Eng., Windsor Univ., Ont., Canada
Abstract :
In this paper, three-layer bidirectional symmetrical and asymmetrical associative memories are presented. The networks possess the desired structural features of a bidirectional associative memory and a three-layer feedforward neural network and are able to learn and recall binary alpha-numeral patterns and gray level images. The network allows two modes of memory recall, namely, recalling by a pattern-pair from both the input and the output layers, and recalling by single-pattern from either the input layer or the output layer. Simulation results on alpha-numeral and face image types of pattern learning and recall problems are provided.
Keywords :
content-addressable storage; feedforward neural nets; image recognition; learning (artificial intelligence); pattern recognition; asymmetrical associative memories; bidirectional associative memory; binary alphanumeral patterns; feedforward neural network; image learning; pattern learning; pattern recall; triple-layer symmetrical associative memories; Application software; Associative memory; Convergence; Feedforward neural networks; Magnesium compounds; Multi-layer neural network; Neural networks; Pattern recognition; Recurrent neural networks; Vectors;
Conference_Titel :
Circuits and Systems, 2005. ISCAS 2005. IEEE International Symposium on
Print_ISBN :
0-7803-8834-8
DOI :
10.1109/ISCAS.2005.1465198
