Locally Connected Oscillatory Networks acting as Fully Connected Oscillatory Networks

被引:0
|
作者
Corinto, Fernando [1 ]
Gilli, Marco [1 ]
Roska, Tamas [2 ,3 ]
机构
[1] Politecn Torino, Dept Elect, Turin, Italy
[2] MTA SZTAKI, Budapest, Hungary
[3] Pazmany Peter Catholic Univ, Fac Informat Technol, Budapest, Hungary
来源
2010 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS | 2010年
关键词
CELLULAR NONLINEAR NETWORKS;
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Oscillatory networks, their archetype being the Turing morphogenesis model, are mathematically represented by large systems of ordinary differential equations and provide an appropriate paradigm for describing many spatial-temporal periodic patterns. The aim of this manuscript is to show that locally connected oscillatory networks (oscillatory CNNs) with linear memoryless and space-invariant interactions may behave as globally connected networks with linear dynamical interactions, if some suitable components of the oscillator state vector are coupled. Space-invariant local connectivity allows to build simple prototype hardware platforms for processing spatial-temporal patterns.
引用
收藏
页码:2047 / 2050
页数:4
相关论文
共 50 条
  • [41] Arrays of several Josephson junctions connected to oscillatory circuit
    Kornev, Victor K.
    Kolotinskiy, Nikolay, V
    INTERNATIONAL CONFERENCE ON MICRO- AND NANO-ELECTRONICS 2018, 2019, 11022
  • [42] A learning model for oscillatory networks
    Nishii, J
    NEURAL NETWORKS, 1998, 11 (02) : 249 - 257
  • [43] Predicting Single-Neuron Activity in Locally Connected Networks
    Azhar, Feraz
    Anderson, William S.
    NEURAL COMPUTATION, 2012, 24 (10) : 2655 - 2677
  • [44] Tangent Bundle Curve Completion with Locally Connected Parallel Networks
    Ben-Yosef, Guy
    Ben-Shahar, Ohad
    NEURAL COMPUTATION, 2012, 24 (12) : 3277 - 3316
  • [45] Locally connected spiking neural networks for unsupervised feature learning
    Saunders, Daniel J.
    Patel, Devdhar
    Hazan, Hananel
    Siegelmann, Hava T.
    Kozma, Robert
    NEURAL NETWORKS, 2019, 119 : 332 - 340
  • [46] Optimal broadcast for fully connected processor-node networks
    Traeff, Jesper Larsson
    Ripke, Andreas
    JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2008, 68 (07) : 887 - 901
  • [47] PHASE-TRANSITIONS IN DILUTE, LOCALLY CONNECTED NEURAL NETWORKS
    STRANDBURG, KJ
    PESHKIN, MA
    BOYD, DF
    CHAMBERS, C
    OKEEFE, B
    PHYSICAL REVIEW A, 1992, 45 (08): : 6135 - 6138
  • [48] Deep fully-connected networks for video compressive sensing
    Iliadis, Michael
    Spinoulas, Leonidas
    Katsaggelos, Aggelos K.
    DIGITAL SIGNAL PROCESSING, 2018, 72 : 9 - 18
  • [49] VLSI FULLY CONNECTED NEURAL NETWORKS FOR THE IMPLEMENTATION OF OTHER TOPOLOGIES
    CARRABINA, J
    LISA, F
    AVELLANA, N
    PEREZVICENTE, CJ
    VALDERRAMA, E
    LECTURE NOTES IN COMPUTER SCIENCE, 1991, 540 : 277 - 284
  • [50] Training Fully Connected Neural Networks is ∃R-Complete
    Bertschinger, Daniel
    Hertrich, Christoph
    Jungeblut, Paul
    Miltzow, Tillmann
    Weber, Simon
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,