Title :
ADAM: an associative neural architecture for invariant pattern classification
Author_Institution :
York Univ., UK
Abstract :
A method for rotation and scale invariant pattern recognition is described. The technique is based upon a simple neural network model allowing massively parallel processing. The method forms an extension to the ADAM (advanced distributed associative memory) system, which is a neural-network-based associative memory. The basics of ADAM are described along with the extension which provides an invariant capability
Keywords :
computerised pattern recognition; content-addressable storage; neural nets; parallel architectures; parallel machines; ADAM; advanced distributed associative memory; associative neural architecture; massively parallel processing; neural network; pattern classification; rotation invariance; scale invariant pattern recognition;
Conference_Titel :
Artificial Neural Networks, 1989., First IEE International Conference on (Conf. Publ. No. 313)
Conference_Location :
London
