Simultaneous embedding of multiple attractor manifolds in a recurrent neural network using constrained gradient optimization

被引:0
|
作者
Agmon, Haggai [1 ,2 ]
Burak, Yoram [1 ]
机构
[1] Hebrew Univ Jerusalem, Jerusalem, Israel
[2] Stanford Univ, Stanford, CA 94305 USA
基金
欧洲研究理事会; 以色列科学基金会;
关键词
PARAMETRIC WORKING-MEMORY; PATH-INTEGRATION; DYNAMICS; MODEL; ORIENTATION; REPRESENTATION; HIPPOCAMPUS; CELLS;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The storage of continuous variables in working memory is hypothesized to be sustained in the brain by the dynamics of recurrent neural networks (RNNs) whose steady states form continuous manifolds. In some cases, it is thought that the synaptic connectivity supports multiple attractor manifolds, each mapped to a different context or task. For example, in hippocampal area CA3, positions in distinct environments are represented by distinct sets of population activity patterns, each forming a continuum. It has been argued that the embedding of multiple continuous attractors in a single RNN inevitably causes detrimental interference: quenched noise in the synaptic connectivity disrupts the continuity of each attractor, replacing it by a discrete set of steady states that can be conceptualized as lying on local minima of an abstract energy landscape. Consequently, population activity patterns exhibit systematic drifts towards one of these discrete minima, thereby degrading the stored memory over time. Here we show that it is possible to dramatically attenuate these detrimental interference effects by adjusting the synaptic weights. Synaptic weight adjustments are derived from a loss function that quantifies the roughness of the energy landscape along each of the embedded attractor manifolds. By minimizing this loss function, the stability of states can be dramatically improved, without compromising the capacity.
引用
收藏
页数:13
相关论文
共 50 条
  • [21] A neural network theory for constrained optimization
    NTT Info. and Commun. Syst. Labs., Yokosuka, 239-0847, Kanagawa, Japan
    Neurocomputing, 1-3 (117-161):
  • [22] Constrained optimization of neural network architecture
    Chiang, M
    2000 IEEE ASIA-PACIFIC CONFERENCE ON CIRCUITS AND SYSTEMS: ELECTRONIC COMMUNICATION SYSTEMS, 2000, : 356 - 359
  • [23] A neural network theory for constrained optimization
    Takahashi, Y
    NEUROCOMPUTING, 1999, 24 (1-3) : 117 - 161
  • [24] Natural Language Inference for Arabic using Recurrent Neural Network and Word Embedding
    Bensghaier, Mabrouka
    Bakari, Wided
    Neji, Mahmoud
    2022 IEEE/ACS 19TH INTERNATIONAL CONFERENCE ON COMPUTER SYSTEMS AND APPLICATIONS (AICCSA), 2022,
  • [25] RECURRENT NEURAL NETWORK LANGUAGE MODEL TRAINING USING NATURAL GRADIENT
    Yu, Jianwei
    Lam, Max. W. Y.
    Chen, Xie
    Hu, Shoukang
    Liu, Songxiang
    Wu, Xixin
    Liu, Xunying
    Meng, Helen
    2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 7260 - 7264
  • [26] A non-penalty recurrent neural network for solving a class of constrained optimization problems
    Hosseini, Alireza
    NEURAL NETWORKS, 2016, 73 : 10 - 25
  • [27] A one-layer recurrent neural network for constrained pseudoconvex optimization and its application for dynamic portfolio optimization
    Liu, Qingshan
    Guo, Zhishan
    Wang, Jun
    NEURAL NETWORKS, 2012, 26 : 99 - 109
  • [28] Enhance Medical Sentiment Vectors through Document Embedding using Recurrent Neural Network
    Yousef, Rami N. M.
    Tiun, Sabrina
    Omar, Nazlia
    Alshari, Eissa M.
    INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS, 2020, 11 (04) : 372 - 378
  • [29] A Word Embedding Based Approach for Focused Web Crawling Using the Recurrent Neural Network
    Dhanith, P. R. Joe
    Surendiran, B.
    Raja, S. P.
    INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE, 2021, 6 (06): : 122 - 132
  • [30] AN IMPROVED APPROACH FOR SOLVING HIERARCHICALLY COUPLED CONSTRAINED OPTIMIZATION PROBLEM IN SIMULTANEOUS OPTIMIZATION OF NEURAL NETWORK STRUCTURE AND WEIGHTS
    Rajora, Manik
    Zou, Pan
    Liang, Steven Y.
    INTERNATIONAL JOURNAL OF INDUSTRIAL ENGINEERING-THEORY APPLICATIONS AND PRACTICE, 2021, 28 (02): : 148 - 161