Title :
Design of Multi-Valued Cellular Neural Networks for Associative Memory
Author :
Zhang, Zhong ; Akiduki, Takuma ; Miyake, Tetsuo ; Imamura, Takashi
Author_Institution :
Dept. of Production Syst. Eng., Toyohashi Univ. of Technol.
Abstract :
This paper discusses the design of multi-valued output functions of cellular neural networks (CNNs) implementing associative memories. The output function of the CNNs is a piecewise linear function which consists of a saturation and non-saturation range. The new structure of the output function is defined, and is called the "basic waveform". The saturation ranges with n levels are generated by adding n-1 basic waveforms. Consequently, creating an associative memory of multi-valued patterns has been successful, and computer experiment results show the validity of the proposed method. The results of this research can expand the range of applications of CNNs as associative memories
Keywords :
cellular neural nets; content-addressable storage; associative memory; multivalue cellular neural network; piecewise linear function; saturation range; Application software; Associative memory; Cellular neural networks; Design engineering; Differential equations; Electronic mail; Neural networks; Piecewise linear techniques; Production systems; Systems engineering and theory; Abnormal detection; Associative memory; Cellular Neural Networks; Multivalued function;
Conference_Titel :
SICE-ICASE, 2006. International Joint Conference
Conference_Location :
Busan
Print_ISBN :
89-950038-4-7
Electronic_ISBN :
89-950038-5-5
DOI :
10.1109/SICE.2006.315057
