Multi-valued cellular neural networks and its application for associative memory

被引：0

作者：

Zhang, Zhong ^{[1
]}

Akiduki, Takuma ^{[1
]}

Miyake, Tetsuo ^{[1
]}

Imamura, Takashi ^{[1
]}

机构：

[1] Toyohashi Univ Technol, 1-1 Hibarigaoka,Tempaku cho, Toyohashi, Aichi 4418580, Japan

来源：

ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 2, PROCEEDINGS | 2007年 / 4492卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

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 multivalued 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.

引用

页码：542 / +

页数：2

共 50 条

[21] Fractal cellular neural networks for associative memory
Southeast Univ, Nanjing, China
Tien Tzu Hsueh Pao, 2 (107-109):
[22] Capacity analysis of the asymptotically stable multi-valued exponential bidirectional associative memory
Wang, CC
Hwang, SM
Lee, JP
IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS PART B-CYBERNETICS, 1996, 26 (05): : 733 - 743
[23] Capacity analysis of the asymptotically stable multi-valued exponential bidirectional associative memory
Natl Sun Yat-Sen Univ, Taiwan
IEEE Trans Syst Man Cybern Part B Cybern, 5 (733-743):
[24] Design and analysis of multi-valued auto-associative quaternion-valued recurrent neural networks based on external inputs
Wang, Yuan
Sha, Chunlin
Zhao, Hongyong
NEUROCOMPUTING, 2021, 444 : 1 - 15
[25] Image processing using cellular neural networks based on multi-valued and universal binary neurons
Igor Aizenberg
Constantine Butakoff
Journal of VLSI signal processing systems for signal, image and video technology, 2002, 32 : 169 - 188
[26] Image processing using cellular neural networks based on multi-valued and universal binary neurons
Aizenberg, I
Butakoff, C
JOURNAL OF VLSI SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2002, 32 (1-2): : 169 - 188
[27] Image processing using cellular neural networks based on multi-valued and universal binary neurons
Aizenberg, I
Aizenberg, N
Bregin, T
Butakov, C
Farberov, E
NEURAL NETWORKS FOR SIGNAL PROCESSING X, VOLS 1 AND 2, PROCEEDINGS, 2000, : 557 - 566
[28] Image processing using cellular neural networks based on multi-valued and universal binary neurons
Aizenberg, Igor
Aizenberg, Naum
Bregin, Taras
Butakov, Constantine
Farberov, Elya
Neural Networks for Signal Processing - Proceedings of the IEEE Workshop, 2000, 2 : 557 - 566
[29] Hybrid cellular automaton/neural network classifier for multi-valued patterns and its VLSI implementation
Democritus Univ of Thrace, Xanthi, Greece
Integr VLSI J, 2 (211-237):
[30] A hybrid cellular automaton neural network classifier for multi-valued patterns and its VLSI implementation
Tzionas, P
Thanailakis, A
Tsalides, P
INTEGRATION-THE VLSI JOURNAL, 1996, 20 (02) : 211 - 237

← 1 2 3 4 5 →