Open AccessA NEURAL NETWORK MODEL FOR UNEQUALLY DISTRIBUTED NEURON STATES AND ITS OPTICAL IMPLEMENTATION
Author(s) -
Shengjiang Chang,
Yue Liu,
Wenwei Zhang,
Jing Shen,
Hongchen Zhai,
Yanxin Zhang
Publication year - 1998
Publication title -
wuli xuebao
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.199
H-Index - 47
ISSN - 1000-3290
DOI - 10.7498/aps.47.1101
Subject(s) - clipping (morphology) , computer science , constraint (computer aided design) , encoding (memory) , artificial neural network , range (aeronautics) , biological neuron model , hopfield network , topology (electrical circuits) , artificial intelligence , mathematics , philosophy , linguistics , geometry , materials science , combinatorics , composite material
To avoid the poor performance of the Hopfield model for unequally distributed neuron states and to alleviate the dynamic range constraint of optical system, a clipped model with asymmetric clipping points is proposed. Apart from its easiness for optical implementation, the capacity and capablilty of noisy tolerance are improved greatly, compared with the former clipped model. In addition, a practical encoding method-beam-direction encoding method is proposed to implement the above clipped model. The preliminary experimental results are given.