Memory Dynamics in Attractor Networks

被引:2
|
作者
Li, Guoqi [1 ]
Ramanathan, Kiruthika [2 ]
Ning, Ning [2 ]
Shi, Luping [1 ]
Wen, Changyun [3 ]
机构
[1] Tsinghua Univ, CBICR, Dept Precis Instrument, Beijing 100084, Peoples R China
[2] ASTAR, Data Storage Inst, Dept Adv Concepts & Nanotechnol ACN, Singapore 117608, Singapore
[3] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore 639798, Singapore
关键词
NEURAL-NETWORKS;
D O I
10.1155/2015/191745
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
As can be represented by neurons and their synaptic connections, attractor networks are widely believed to underlie biological memory systems and have been used extensively in recent years to model the storage and retrieval process of memory. In this paper, we propose a new energy function, which is nonnegative and attains zero values only at the desired memory patterns. An attractor network is designed based on the proposed energy function. It is shown that the desired memory patterns are stored as the stable equilibrium points of the attractor network. To retrieve a memory pattern, an initial stimulus input is presented to the network, and its states converge to one of stable equilibrium points. Consequently, the existence of the spurious points, that is, local maxima, saddle points, or other local minima which are undesired memory patterns, can be avoided. The simulation results show the effectiveness of the proposed method.
引用
收藏
页数:7
相关论文
共 50 条
  • [1] Memory Dynamics in Attractor Networks with Saliency Weights
    Tang, Huajin
    Li, Haizhou
    Yan, Rui
    [J]. NEURAL COMPUTATION, 2010, 22 (07) : 1899 - 1926
  • [2] Learning Attractor Dynamics for Generative Memory
    Wu, Yan
    Wayne, Greg
    Gregor, Karol
    Lillicrap, Timothy
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018), 2018, 31
  • [3] Attractor Networks and the Dynamics of Visual Perception
    Braun, J.
    Deco, G.
    [J]. PERCEPTION, 2013, 42 : 4 - 4
  • [4] Attractor dynamics in local neuronal networks
    Thivierge, Jean-Philippe
    Comas, Rosa
    Longtin, Andre
    [J]. FRONTIERS IN NEURAL CIRCUITS, 2014, 8
  • [5] Attractor dynamics in local neuronal networks
    Rosa Comas
    André Longtin
    Jean-Philippe Thivierge
    [J]. BMC Neuroscience, 14 (Suppl 1)
  • [6] Attractor dynamics in feedforward neural networks
    Saul, LK
    Jordan, MI
    [J]. NEURAL COMPUTATION, 2000, 12 (06) : 1313 - 1335
  • [7] Attractor dynamics in realistic hippocampal networks
    Menschik, ED
    Yen, SC
    Finkel, LH
    [J]. COMPUTATIONAL NEUROSCIENCE: TRENDS IN RESEARCH, 1998, : 465 - 470
  • [8] Synaptic Potentiation Facilitates Memory-like Attractor Dynamics in Cultured In Vitro Hippocampal Networks
    Niedringhaus, Mark
    Chen, Xin
    Conant, Katherine
    Dzakpasu, Rhonda
    [J]. PLOS ONE, 2013, 8 (03):
  • [9] A Memory-Based STDP Rule for Stable Attractor Dynamics in Boolean Recurrent Neural Networks
    Cabessa, Jeremie
    Villa, Alessandro
    [J]. 2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [10] Attractor states of Boolean dynamics in complex networks
    Kinoshita, Shu-Ichi
    Iguchi, Kazumoto
    Yamada, Hiroaki S.
    [J]. PROGRESS OF THEORETICAL PHYSICS SUPPLEMENT, 2008, (173): : 342 - 350