Title :
A practical neural network for handwritten character recognition built by dynamics-based active learning and self-organization of feedback mechanism
Author :
Natori, Naotake ; Nishimura, Kazuo
Author_Institution :
Neural Syst. Toshiba Lab., RWCP, Kanagawa, Japan
Abstract :
A feedback mechanism which enhances similarity between recognition by a human and that by an artificial neural network we have proposed is introduced. A human may turn his attention to a particular portion of the object in order to classify it successfully. It is regarded as a feedback from the first rough classification to the final one. The proposed feedback mechanism is designed to simulate such attention. The recognition rates by a neural network with the feedback mechanism exceed those by a former neural network
Keywords :
character recognition; feedback; learning (artificial intelligence); pattern classification; self-organising feature maps; vector quantisation; dynamics-based active learning; feedback mechanism; handwritten character recognition; learning vector quantisation; neural network; selective attention; self-organization; Artificial neural networks; Character recognition; Fingers; Handwriting recognition; Humans; Laboratories; Neural networks; Neurofeedback; Pattern recognition; Predictive models;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487277
