Inhibitory Connections in the Assembly Neural Network for Texture Segmentation
Abstract
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.
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.
Recommended Citation
A. Goltsev and D. C. Wunsch, "Inhibitory Connections in the Assembly Neural Network for Texture Segmentation," Neural Networks, vol. 11, no. 5, pp. 951 - 962, Elsevier, Jan 1998.
The definitive version is available at https://doi.org/10.1016/S0893-6080(98)00053-7
Department(s)
Electrical and Computer Engineering
International Standard Serial Number (ISSN)
0893-6080
Document Type
Article - Journal
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 1998 Elsevier, All rights reserved.
Publication Date
01 Jan 1998
