QUALITY AND EFFICIENCY OF RETRIEVAL FOR WILLSHAW-LIKE AUTOASSOCIATIVE NETWORKS .1. CORRECTION

被引：3
|
作者：
FROLOV, A
KARTASHOV, A
GOLTSEV, A
FOLK, R
机构：
来源：
NETWORK-COMPUTATION IN NEURAL SYSTEMS | 1995年 / 6卷 / 04期
关键词：
D O I：
10.1088/0954-898X/6/4/001
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The informational properties of a neural network model of an autoassociative memory based on binary Hebbian synapses are investigated. The model is a modification of the Willshaw network with a floating threshold which keeps approximately constant the number of active neurons (winners) at each time step. In the asymptotic case of large number of neurons, informational characteristics have been calculated analytically for single-step correction. Comparison with simulations shows that the maximal correction efficiency attains its asymptotic values for networks with surprisingly small number of neurons. Simulation results for multistep correction show considerable improvement over the single-step case.
引用
收藏
页码：513 / 534
页数：22
相关论文
共 25 条
  • [1] QUALITY AND EFFICIENCY OF RETRIEVAL FOR WILLSHAW-LIKE AUTOASSOCIATIVE NETWORKS .2. RECOGNITION
    FROLOV, A
    KARTASHOV, A
    GOLTSEV, A
    FOLK, R
    NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1995, 6 (04) : 535 - 549
  • [2] Quality and efficiency of retrieval for Willshaw-like autoassociative networks .3. Willshaw-Potts model
    Kartashov, A
    Frolov, A
    Goltsev, A
    Folk, R
    NETWORK-COMPUTATION IN NEURAL SYSTEMS, 1997, 8 (01) : 71 - 86
  • [3] INFORMATION-RETRIEVAL IN NEURAL NETWORKS .1. EIGENPROBLEMS IN NEURAL NETWORKS
    MARUANI, AD
    CHEVALLIER, RC
    SIRAT, GY
    REVUE DE PHYSIQUE APPLIQUEE, 1987, 22 (10): : 1321 - 1325
  • [4] On Synthesis and Optimization of Steam System Networks. 1. Sustained Boiler Efficiency
    Majozi, Thokozani
    Price, Tim
    INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2010, 49 (19) : 9143 - 9153
  • [5] PROTEIN QUALITY OF TRITICALE .1. EARLY GENERATION SELECTION FOR PROTEIN EFFICIENCY INDEXES
    KNOBLAUCH, CJ
    ELLIOTT, FC
    CROP SCIENCE, 1977, 17 (02) : 267 - 269
  • [6] METHODOLOGY FOR DESIGNING AIR-QUALITY MONITORING NETWORKS .1. THEORETICAL ASPECTS
    LIU, MK
    AVRIN, J
    POLLACK, RI
    BEHAR, JV
    MCELROY, JL
    ENVIRONMENTAL MONITORING AND ASSESSMENT, 1986, 6 (01) : 1 - 11
  • [7] The Use of Bayesian Networks to Assess the Quality of Evidence from Research Synthesis: 1.
    Stewart, Gavin B.
    Higgins, Julian P. T.
    Schuenemann, Holger
    Meader, Nick
    PLOS ONE, 2015, 10 (04):
  • [8] The New Volcanic Ash Satellite Retrieval VACOS Using MSG/SEVIRI and Artificial Neural Networks: 1. Development
    Piontek, Dennis
    Bugliaro, Luca
    Schmidl, Marius
    Zhou, Daniel K.
    Voigt, Christiane
    REMOTE SENSING, 2021, 13 (16)
  • [9] COMPUTERIZED LIQUID SCINTILLATION-COUNTING DATA MANAGEMENT .1. TIME SEQUENCE FOR DECAY CORRECTION - KEY FOR DATA STORAGE AND RETRIEVAL
    AARON, CS
    LEE, WR
    ANALYTICAL BIOCHEMISTRY, 1975, 65 (1-2) : 573 - 577
  • [10] Reliability and Efficiency Determination in Medium-Voltage Networks as a Function of Neutral-Point Approach - 1.
    Fiedler, Herbert
    1978, 32 (12): : 648 - 649
123