Title :
Stochastic searching networks
Author_Institution :
Reading Univ., UK
Abstract :
A fundamental difficulty when using neural networks applied to problems of pattern recognition is that of stimulus equivalence: the ability to classify a pattern, independent of position, rotation or scale, within the search space. The paper describes how a network of stochastic cells can be used to find an efficient solution to such problems
Keywords :
neural nets; pattern recognition; search problems; neural networks; pattern recognition; search space; stimulus equivalence; stochastic searching networks;
Conference_Titel :
Artificial Neural Networks, 1989., First IEE International Conference on (Conf. Publ. No. 313)
Conference_Location :
London
