Inhibitory connections in the assembly neural network for texture segmentation

被引：7
|
作者：
Goltsev, A
Wunsch, DC
机构：
[1] Ukrainian Acad Sci, Cybernet Ctr, UA-252650 Kiev, Ukraine
[2] Texas Tech Univ, Dept Elect Engn, Appl Computat Intelligence Lab, Lubbock, TX 79409 USA
来源：
NEURAL NETWORKS | 1998年 / 11卷 / 05期
关键词：
connection matrix; excitatory connections; inhibitory connections; negative features; neural assemblies; neurons; subnetworks; texture segmentation;
D O I：
10.1016/S0893-6080(98)00053-7
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A neural network with assembly organization is described. This assembly network is applied to the problem of texture segmentation in natural scenes. The network is partitioned into several subnetworks: one for each texture class. Hebb's assemblies are formed in the subnetworks during the process of training the excitatory connections. Also, a structure of the inhibitory connections is formed in the assembly network during a separate training process. The inhibitory connections result in inhibitory interactions between different subnetworks. Computer simulation of the network has been performed. Experiments show that an adequately trained assembly network with inhibitory connections is more efficient than without them. (C) 1998 Elsevier Science Ltd. All rights reserved.
引用
收藏
页码：951 / 962
页数：12
相关论文
共 50 条
  • [41] Online workbenches for neural network connections
    Bota, Mihail
    Swanson, Larry W.
    JOURNAL OF COMPARATIVE NEUROLOGY, 2007, 500 (05) : 807 - 814
  • [42] Neural network for image segmentation
    Skourikhine, AN
    Prasad, L
    Schlei, BR
    APPLICATIONS AND SCIENCE OF NEURAL NETWORKS, FUZZY SYSTEMS, AND EVOLUTIONARY COMPUTATION III, 2000, 4120 : 28 - 35
  • [43] A neural network based segmentation
    Spyridonos, P
    Cavouras, D
    Makris, V
    Zenebissis, G
    Maratou, V
    Kagadis, GC
    Ravazoula, P
    Nikiforidis, GC
    MEDICON 2001: PROCEEDINGS OF THE INTERNATIONAL FEDERATION FOR MEDICAL & BIOLOGICAL ENGINEERING, PTS 1 AND 2, 2001, : 546 - 549
  • [44] Dynamical response of an excitatory-inhibitory neural network to external stimulation: An application to image segmentation
    Sinha, S
    Basak, J
    PHYSICAL REVIEW E, 2002, 65 (04):
  • [45] Dynamical response of an excitatory-inhibitory neural network to external stimulation: An application to image segmentation
    Sinha, Sitabhra
    Basak, Jayanta
    Physical Review E - Statistical, Nonlinear, and Soft Matter Physics, 2002, 65 (04): : 1 - 046112
  • [46] PATCH-BASED FULLY CONVOLUTIONAL NEURAL NETWORK WITH SKIP CONNECTIONS FOR RETINAL BLOOD VESSEL SEGMENTATION
    Feng, Zhongwei
    Yang, Jie
    Yao, Lixiu
    2017 24TH IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2017, : 1742 - 1746
  • [47] Random neural network texture model
    Gelenbe, E
    Hussain, K
    Abdelbaki, H
    APPLICATIONS OF ARTIFICIAL NEURAL NETWORKS IN IMAGE PROCESSING V, 2000, 3962 : 104 - 111
  • [48] Texture synthesis by a neural network model
    B. B. Chaudhuri
    P. Kundu
    Neural Computing & Applications, 1997, 6 : 2 - 11
  • [49] Texture synthesis by a neural network model
    Chaudhuri, BB
    Kundu, P
    NEURAL COMPUTING & APPLICATIONS, 1997, 6 (01): : 2 - 11
  • [50] STRUCTURED NEURAL NETWORKS WITH LEARNING FOR TEXTURE SEGMENTATION IN IMAGES
    GOLTSEV, AD
    CYBERNETICS AND SYSTEMS ANALYSIS, 1991, 27 (06) : 927 - 936
12345