Dynamics about neural array with simple lateral inhibitory connections

Abstract

Lateral inhibitory effect is a well-known feature of information processing in neural systems. This paper presents a neural array model with simple lateral inhibitory connections. After detailed examining into the dynamics of this kind of neural array, the author gives the sufficient conditions under which the outputs of the network will tend to a special stable pattern called spatial sparse pattern in which if the output of a neuron is 1, then the outputs of the neurons in its neighborhood are 0. This ability called spatial sparse coding plays an important role in self-coding, self-organization and associative memory for patterns and pattern sequences. The main conclusions about the dynamics of this kind of neural array which is related to spatial sparse coding are introduced.

Keywords

Simple lateral inhibitory connections / Spatial sparse coding / Spatial sparse pattern / Neural array

References

[1] Amari S.. Homogeneneous nets of neuron-like elements. Biological Cybernetics, 1975, 17: 211-230

[2] Amari S.. Dynamics of pattern formation in lateral-inhibition type neural fields. Biological Cybernetics, 1977, 27: 77-87

[3] Coleman B. P.. Mathematical theory of lateral sensory inhibition. Arch. Rat. Mach. Analysis, 1971, 43: 79-100

[4] Ellias S. A., Grossgerg S.. Pattern formation, contrast control and oscillations in the short-term memory of shunting on-center off-surround network. Biological Cybernetics, 1975, 20: 69-98

[5] Griffith J. S.. A field theory of neural nets I. Bull. Math. Biophys, 1963, 25: 111-120

[6] Griffith J. S.. A field theory of neural nets II. Bull. Math. Biophys, 1965, 27: 187-195

[7] Wilson H. R., Cowan J. D.. Excitatory and inhibitory interactions in local populations of model neurons. Biophysical J., 1972, 12: 1-24

[8] Zhuang, J., Spatial Sparse Coding networks with simple lateral inhibitory neural array and its application in information security and secrete communication, Neural Computation, 2010, present.

[9] Zhuang, J., Associative network model with hidden layer for pattern sequences, Neural Computation, 2010, present.

[10] Zhuang, J., Self-coding network for pattern sequences and its application in secrete communication, Neural Computation, 2010, present.

[11] Zhuang, J., Self-organization for formation of category detecting neurons, Neural Computation, 2010, present.

[12] Chua L. O., Yang L.. Cellular neural networks: theory. IEEE Trans., Circuit and System, 1988, 35(10): 1253-1273

[13] Slavova A., Mladenov V.. Cellular Neural Networks: Theory and Applications, 2004, New York: Nova Science Publisher