STRUCTURAL PHASE TRANSITIONS IN NEURAL NETWORKS

被引：2

作者：

Turova, Tatyana S. ^{[1
]}

机构：

[1] Lund Univ, Ctr Math, S-22100 Lund, Sweden

来源：

MATHEMATICAL BIOSCIENCES AND ENGINEERING | 2014年 / 11卷 / 01期

关键词：

Integrate-and-fire neurons; random graphs; bootstrap percolation; neural networks; SPATIOTEMPORAL PATTERNS; BOOTSTRAP PERCOLATION; SEQUENCES; PLASTICITY; EMERGENCE; MODEL;

D O I：

10.3934/mbe.2014.11.139

中图分类号：

Q [生物科学];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

A model is considered for a neural network that is a stochastic process on a random graph. The neurons are represented by "integrate-and-fire" processes. The structure of the graph is determined by the probabilities of the connections, and it depends on the activity in the network. The dependence between the initial level of sparseness of the connections and the dynamics of activation in the network was investigated. A balanced regime was found between activity, i.e., the level of excitation in the network, and inhibition, that allows formation of synfire chains.

引用

页码：139 / 148

页数：10

共 50 条

[31] STRUCTURAL PHASE TRANSITIONS IN A DISCRETE ONE-DIMENSIONAL CHAIN
Vedantam, Srikanth
Mohanraj, S.
INTERNATIONAL JOURNAL OF APPLIED MECHANICS, 2009, 1 (03) : 545 - 556
[32] Modeling exchange rates: Smooth transitions, neural networks, and linear models
Medeiros, MC
Veiga, A
Pedreira, CE
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2001, 12 (04): : 755 - 764
[33] A nonlinear journey from structural phase transitions to quantum annealing
Thudiyangal, Mithun
Kevrekidis, Panayotis G.
Saxena, Avadh
Bishop, Alan R.
CHAOS, 2024, 34 (05)
[34] Inter-Frequency Phase Difference for Phase Reconstruction Using Deep Neural Networks and Maximum Likelihood
Thien, Nguyen Binh
Wakabayashi, Yukoh
Iwai, Kenta
Nishiura, Takanobu
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2023, 31 : 1667 - 1680
[35] Structural models and topology design of rapid neural networks
Al Rababaa, MS
Computer Graphics, Imaging and Vision: New Trends, 2005, : 181 - 186
[36] HOBAT: Batch Verification for Homogeneous Structural Neural Networks
Li, Jingyang
Li, Guoqiang
2023 38TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING, ASE, 2023, : 1276 - 1287
[37] Prediction of time series by a structural learning of neural networks
Ishikawa, M
Moriyama, T
FUZZY SETS AND SYSTEMS, 1996, 82 (02) : 167 - 176
[38] Structural Coverage Criteria for Neural Networks Could Be Misleading
Li, Zenan
Ma, Xiaoxing
Xu, Chang
Cao, Chun
2019 IEEE/ACM 41ST INTERNATIONAL CONFERENCE ON SOFTWARE ENGINEERING: NEW IDEAS AND EMERGING RESULTS (ICSE-NIER 2019), 2019, : 89 - 92
[39] An overview of structural coverage metrics for testing neural networks
Usman, Muhammad
Sun, Youcheng
Gopinath, Divya
Dange, Rishi
Manolache, Luca
Pasareanu, Corina S.
INTERNATIONAL JOURNAL ON SOFTWARE TOOLS FOR TECHNOLOGY TRANSFER, 2023, 25 (03) : 393 - 405
[40] Phase harmonic correlations and convolutional neural networks
Mallat, Stephane
Zhang, Sixin
Rochette, Gaspar
INFORMATION AND INFERENCE-A JOURNAL OF THE IMA, 2020, 9 (03) : 721 - 747

← 1 2 3 4 5 →