Title :
A cellular system for pattern recognition using associative neural networks
Author :
Orovas, Christos ; Austin, James
Author_Institution :
Dept. of Comput. Sci., York Univ., UK
Abstract :
A cellular system for pattern recognition is presented. The cells are placed in a two dimensional array and they are capable of performing basic symbolic processing and exchanging messages about their state. Following a cellular automata like operation the aim of the system is to transform an initial symbolic description of a pattern to a correspondent object level representation. To this end, a hierarchical approach for the description of the structure of the patterns is followed. The underlying processing engine of the system is the AURA model of associative memory. The system is endowed with a learning mechanism utilizing the distributed nature of the architecture. A dedicated hardware platform is also available
Keywords :
array signal processing; associative processing; cellular automata; cellular neural nets; content-addressable storage; image recognition; 2D array; AURA model; associative memory; associative neural networks; cellular automata like operation; cellular system; dedicated hardware platform; hierarchical approach; learning mechanism; message exchange; object level representation; pattern recognition; symbolic description; symbolic processing; Associative memory; Cellular networks; Cellular neural networks; Computer architecture; Computer science; Computer vision; Hardware; Learning systems; Neural networks; Pattern recognition;
Conference_Titel :
Cellular Neural Networks and Their Applications Proceedings, 1998 Fifth IEEE International Workshop on
Conference_Location :
London
Print_ISBN :
0-7803-4867-2
DOI :
10.1109/CNNA.1998.685353
