Positive and negative circuits in discrete neural networks

被引：55

作者：

Aracena, J ^{[1
]}

Demongeot, J

Goles, E

机构：

[1] Univ Chile, DIM, Santiago 1703, Chile

[2] Univ Chile, Ctr Modelamiento Matemat, Santiago 1703, Chile

[3] IAB Fac Med, UMR CNRS 5525, IMAG, TIMC, F-38706 La Tronche, France

来源：

IEEE TRANSACTIONS ON NEURAL NETWORKS | 2004年 / 15卷 / 01期

关键词：

discrete neural networks (DNNs); fixed points; graph; positive and negative circuits; positive feedback vertex sets;

D O I：

10.1109/TNN.2003.821555

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We study the relationships between the positive and negative circuits of the connection graph and the fixed points of discrete neural networks (DNNs). As main results, we give necessary conditions and sufficient conditions for the existence of fixed points in a DNN. Moreover, we exhibit an upper bound for the number of fixed points in terms of the structure and number of positive circuits in the connection graph. This allows the determination of the maximum capacity for storing vectors in DNNs as fixed points, depending on the architecture of the network.

引用

页码：77 / 83

页数：7

共 50 条

[1] NEURAL CIRCUITS ASSOCIATED WITH POSITIVE AND NEGATIVE SELF-APPRAISAL
Bruehl, A. B.
Rufer, M.
Kaffenberger, T.
Baur, V.
Herwig, U.
NEUROSCIENCE, 2014, 265 : 48 - 59
[2] OPEN RANDOM NETWORKS WITH NEGATIVE AND POSITIVE CUSTOMERS, AND NEURAL NETWORKS
GELENBE, E
COMPTES RENDUS DE L ACADEMIE DES SCIENCES SERIE II, 1989, 309 (10): : 979 - 982
[3] Implementation of optical sensory neural networks by simple discrete and monolithic circuits
Nabet, Bahram
Darling, Robert B.
Neural Networks, 1988, 1 (1 SUPPL)
[4] Negative Can Be Positive: Signed Graph Neural Networks for Recommendation
Huang, Junjie
Xie, Ruobing
Cao, Qi
Shen, Huawei
Zhang, Shaoliang
Xia, Feng
Cheng, Xueqi
INFORMATION PROCESSING & MANAGEMENT, 2023, 60 (04)
[5] Random Neural Networks with Negative and Positive Signals and Product Form Solution
Gelenbe, Erol
NEURAL COMPUTATION, 1989, 1 (04) : 502 - 510
[6] Discrete combinatorial circuits emerging in neural networks: A mechanism for rules of grammar in the human brain?
Pulvermueller, Friedemann
Knoblauch, Andreas
NEURAL NETWORKS, 2009, 22 (02) : 161 - 172
[7] Neural Networks for Logic Circuits
Liu Yongcai (School of Computer Engineering and Science)
Advances in Manufacturing, 1998, (02) : 60 - 63
[8] Neural networks for logic circuits
Journal of Shanghai University, 1998, 2 (02): : 144 - 147
[9] Spatial Differentiation and Positive Circuits in a Discrete Framework
Crumiere, Anne
Ruet, Paul
ELECTRONIC NOTES IN THEORETICAL COMPUTER SCIENCE, 2008, 192 (03) : 85 - 100
[10] Positive Neural Networks in Discrete Time Implement Monotone-Regular Behaviors
Ameloot, Tom J.
Van den Bussche, Jan
NEURAL COMPUTATION, 2015, 27 (12) : 2623 - 2660

← 1 2 3 4 5 →