Chapter XIV A Mathematical Theory of Self-Organizing Nerve Systems

Publisher Summary This chapter presents a mathematical theory of self-organizing nerve systems. It treats the general equation of neural learning in a unified manner. Thus, perceptron learning, correlation learning for associative memory, and automatic formation of signal or featured detectors are studied in this common frame. The chapter presents a mathematical method of analyzing a wide class of nerve systems. A number of self-organizing nerve systems are analyzed by this method. Though the mathematical analysis is carried into effect only under some bold mathematical simplifications, the behavior of the simplified models are believed to show, at least qualitatively, the same behavior as more realistic models have. Hence, the method is useful in analyzing nervous systems and in building more realistic models. The chapter also discusses the dynamics of neural excitations.

[1]  S. Amari,et al.  Competition and Cooperation in Neural Nets , 1982 .

[2]  E M Harth,et al.  Dynamics of neural structures. , 1970, Journal of theoretical biology.

[3]  J. Cowan,et al.  Excitatory and inhibitory interactions in localized populations of model neurons. , 1972, Biophysical journal.

[4]  Shun-Ichi Amari,et al.  Topographic organization of nerve fields , 1979, Neuroscience Letters.

[5]  S. Amari,et al.  Existence and stability of local excitations in homogeneous neural fields , 1979, Journal of mathematical biology.

[6]  E. Caianiello.  Outline of a theory of thought-processes and thinking machines. , 1961, Journal of theoretical biology.

[7]  D Marr,et al.  Cooperative computation of stereo disparity. , 1976, Science.

[8]  Roman Bek,et al.  Discourse on one way in which a quantum-mechanics language on the classical logical base can be built up , 1978, Kybernetika.

[9]  C. Malsburg,et al.  How patterned neural connections can be set up by self-organization , 1976, Proceedings of the Royal Society of London. Series B. Biological Sciences.

[10]  S. Amari,et al.  A Mathematical Foundation for Statistical Neurodynamics , 1977 .

[11]  S. Geman.  SOME AVERAGING AND STABILITY RESULTS FOR RANDOM DIFFERENTIAL EQUATIONS , 1979 .

[12]  Shun-ichi Amari,et al.  Characteristics of randomly connected threshold-element networks and network systems , 1971 .

[13]  S. Amari,et al.  Characteristics of Random Nets of Analog Neuron-Like Elements , 1972, IEEE Trans. Syst. Man Cybern..

[14]  E M Harth,et al.  Brain functions and neural dynamics. , 1970, Journal of theoretical biology.

[15]  Shun-ichi Amari,et al.  Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements , 1972, IEEE Transactions on Computers.