Hyperbolic-Valued Hopfield Neural Networks in Synchronous Mode

被引：4
作者：
Kobayashi, Masaki [1 ]
机构：
[1] Univ Yamanashi, Ctr Math Sci, Kofu, Yamanashi 4008511, Japan
来源：
NEURAL COMPUTATION | 2020年 / 32卷 / 09期
关键词：
ASSOCIATIVE MEMORY;
D O I：
10.1162/neco_a_01303
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
For most multistate Hopfield neural networks, the stability conditions in asynchronous mode are known, whereas those in synchronous mode are not. If they were to converge in synchronous mode, recall would be accelerated by parallel processing. Complex-valued Hopfield neural networks (CHNNs) with a projection rule do not converge in synchronous mode. In this work, we provide stability conditions for hyperbolic Hopfield neural networks (HHNNs) in synchronous mode instead of CHNNs. HHNNs provide better noise tolerance than CHNNs. In addition, the stability conditions are applied to the projection rule, and HHNNs with a projection rule converge in synchronous mode. By computer simulations, we find that the projection rule for HHNNs in synchronous mode maintains a high noise tolerance.
引用
收藏
页码：1685 / 1696
页数：12
相关论文
共 37 条
[1]  
[Anonymous], 2009, LEARNING MULTIPLE LA
[2]  
Aoki H, 2002, ICONIP'02: PROCEEDINGS OF THE 9TH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING, P1084
[3]  
Aoki H, 2000, INT C PATT RECOG, P626, DOI 10.1109/ICPR.2000.906153
[4]   Continuous-Valued Quaternionic Hopfield Neural Network for Image Retrieval: A Color Space Study [J].
de Castro, Fidelis Zanetti ;
Valle, Marcos Eduardo .
2017 6TH BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), 2017, :186-191
[5]  
Hirose A, 2012, STUD COMPUT INTELL, V400, P1, DOI 10.1007/978-3-64227632-3
[6]  
Hirose A., 2003, Complex-Valued Neural Networks: Theories and Applications
[7]  
Hirose A., 2013, Complex-Valued Neural Networks: Advances and Applica- tions
[8]  
ISOKAWA T, 2010, IEEE IJCNN, P1281
[9]  
ISOKAWA T, 2012, IEEE IJCNN, P1246
[10]  
Isokawa T., 2008, P SCIS ISIS SCIS ISI, P809
1234