Title :
The effective weighting method of CNN as a recall
Author :
Mizutani, Hikaru
Author_Institution :
Shonan Inst. of Technol., Kanagawa, Japan
Abstract :
A synthesis method for determining weights for association in a cellular neural network (CNN) is presented. The weights determined by the method are given. The associative operation of a CNN is simulated by using the resulting weights. The CNN utilizing the proposed weighting method recalls all fundamental memories
Keywords :
content-addressable storage; neural nets; pattern recognition; CNN; associative operation; cellular neural network; memory recalls; weighting method; Artificial intelligence; Cellular neural networks; Equations; Error correction; Hopfield neural networks; Network synthesis; Neural networks; Neurons; Sparse matrices;
Conference_Titel :
Cellular Neural Networks and their Applications, 1992. CNNA-92 Proceedings., Second International Workshop on
Conference_Location :
Munich
Print_ISBN :
0-7803-0875-1
DOI :
10.1109/CNNA.1992.274350
