A neural network model for visual selection and shifting

被引:4
|
作者
Qiao, Yuanhua [1 ]
Liu, Xiaojie [1 ]
Miao, Jun [2 ]
Duan, Lijuan [3 ]
机构
[1] Beijing Univ Technol, Coll Appl Sci, Beijing 100124, Peoples R China
[2] Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China
[3] Beijing Univ Technol, Coll Comp Sci, Beijing 100124, Peoples R China
基金
北京市自然科学基金;
关键词
Visual selection and shifting; neural network; periodic activity; synchronization; mapping dynamic system; ATTENTION;
D O I
10.1142/S0219635216500205
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
In this paper, a two-layer network is built to simulate the mechanism of visual selection and shifting based on the mapping dynamic model for instantaneous frequency. Unlike the differential equation model using limit cycle to simulate neuron oscillation, we build an instantaneous frequency mapping dynamic model to describe the change of the neuron frequency to avoid the difficulty of generating limit cycle. The activity of the neuron is rebuilt based on the instantaneous frequency and in this work, we use the first layer of neurons to implement image segmentation and the second layer of neurons to act as visual selector. The frequency of the second neuron (central neuron) is always changing, while central neuron resonates with the neurons corresponding to an object, the object is selected, then with the central neuron frequency changing, the selected object loses attention, the process goes on.
引用
收藏
页码:321 / 335
页数:15
相关论文
共 50 条
  • [1] A neural network architecture for visual selection
    Amit, Y
    NEURAL COMPUTATION, 2000, 12 (05) : 1141 - 1164
  • [2] THE MODEL OF A NEURAL NETWORK VISUAL PREPROCESSOR
    RYBAK, IA
    SHEVTSOVA, NA
    SANDLER, VM
    NEUROCOMPUTING, 1992, 4 (1-2) : 93 - 102
  • [3] Model selection for neural network classification
    Lee H.K.H.
    Journal of Classification, 2001, 18 (2) : 227 - 243
  • [4] Model selection for neural network classification
    Lee, HKH
    JOURNAL OF CLASSIFICATION, 2001, 18 (02) : 227 - 243
  • [5] A neural network model of visual till aftereffects
    Bednar, JA
    Miikkulainen, R
    PROCEEDINGS OF THE NINETEENTH ANNUAL CONFERENCE OF THE COGNITIVE SCIENCE SOCIETY, 1997, : 37 - 42
  • [6] A neural network approach to forecasting model selection
    Department of Decision Sciences, Whittemore School of Business and Economics, University of New Hampshire, Durham, New Hampshire NH 03824, United States
    Inf Manage, 6 (297-303):
  • [7] A parallel algorithm for selection on a neural network model
    El-Horbaty, EM
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-V, 2000, : 1187 - 1190
  • [8] Signal generation and selection in a neural network model
    Tateno, K
    Hayashi, H
    Ishizuka, S
    BRAIN-INSPIRED IT I, 2004, 1269 : 117 - 120
  • [9] A neural network model approach to athlete selection
    Maszczyk A.
    Zajac A.
    Ryguła I.
    Sports Engineering, 2011, 13 (2) : 83 - 93
  • [10] A neural network approach to forecasting model selection
    Sohl, JE
    Venkatachalam, AR
    INFORMATION & MANAGEMENT, 1995, 29 (06) : 297 - 303