ROBUSTNESS AGAINST RANDOM DILUTION IN ATTRACTOR NEURAL NETWORKS

被引：9

作者：

KOMODA, A ^{[1
]}

SERNEELS, R ^{[1
]}

WONG, KYM ^{[1
]}

BOUTEN, M ^{[1
]}

机构：

[1] UNIV OXFORD,DEPT THEORET PHYS,OXFORD OX1 3NP,ENGLAND

来源：

JOURNAL OF PHYSICS A-MATHEMATICAL AND GENERAL | 1991年 / 24卷 / 13期

关键词：

D O I：

10.1088/0305-4470/24/13/008

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

We study the robustness of attractor neural networks against random disruption of a fraction of the synaptic couplings. For the maximally stable network (MSN), we determine the effect of different degrees of dilution on the overall storage capacity, the size of the basins of attraction and the attractor overlap. Comparison with corresponding results for the Hopfield model indicates that, although MSN is more robust at low degrees of dilution, the Hopfield network becomes more robust at high dilution.

引用

页码：L743 / L749

页数：7

共 50 条

[1] THE PRINCIPLE OF ADAPTATION AND DILUTION ROBUSTNESS IN NEURAL NETWORKS
WONG, KYM
BOUTEN, M
[J]. EUROPHYSICS LETTERS, 1991, 16 (06): : 525 - 530
[2] EFFECT OF SYNAPSE DILUTION ON THE MEMORY RETRIEVAL IN STRUCTURED ATTRACTOR NEURAL NETWORKS
BRUNEL, N
[J]. JOURNAL DE PHYSIQUE I, 1993, 3 (08): : 1693 - 1715
[3] Effect of random synaptic dilution in oscillator neural networks
Aoyagi, T
Kitano, K
[J]. PHYSICAL REVIEW E, 1997, 55 (06): : 7424 - 7428
[4] Robustness of attractor states in complex networks
Kinoshita, Shu-Ichi
Iguchi, Kazumoto
Yamada, Hiroaki S.
[J]. COMPLEX SYSTEMS-BOOK 1, 2008, 982 : 768 - +
[5] Adversarial Robustness Guarantees for Random Deep Neural Networks
De Palma, Giacomo
Kiani, Bobak T.
Lloyd, Seth
[J]. INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
[6] Robustness of random networks with selective reinforcement against attacks
Kawasumi, Tomoyo
Hasegawa, Takehisa
[J]. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS, 2024, 649
[7] Robustness of Neural Ensembles Against Targeted and Random Adversarial Learning
Wang, Shir Li
Shafi, Kamran
Lokan, Chris
Abbass, Hussein A.
[J]. 2010 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE 2010), 2010,
[8] Advantages of dilution in the connectivity of attractor networks in the brain
Rolls, Edmund T.
[J]. BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES, 2012, 1 : 44 - 54
[9] Training Neural Networks with Random Noise Images for Adversarial Robustness
Park, Ji-Young
Liu, Lin
Li, Jiuyong
Liu, Jixue
[J]. PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 3358 - 3362
[10] A Study on Robustness of Complex Networks against Random Node Removals
Yamashita, Kazuyuki
Nakamura, Ryo
Ohsaki, Hiroyuki
[J]. 2018 IEEE 42ND ANNUAL COMPUTER SOFTWARE AND APPLICATIONS CONFERENCE (COMPSAC), VOL 1, 2018, : 966 - 969

← 1 2 3 4 5 →