论文信息 - An unpredictable-dynamics approach to neural intelligence

An unpredictable-dynamics approach to neural intelligence

The theoretical basis for a dynamic neural network architecture that takes advantage of the notion of terminal chaos to process information in a way that is phenomenologically similar to brain activity is presented. The architecture exploits the phenomenology of nonlinear dynamic systems as an alternative to the traditional paradigm of finite-state machines. It is based on some effects of nonLipschitzian dynamics. The nonlinear phenomenon of terminal chaos and its relevance to brain activity are examined.<<ETX>>

Michail Zak | M. Zak

[1] Michail Zak,et al. Spontaneously Activated Systems in Neurodynamics , 1989, Complex Syst..

[2] M. Zak. Non-Lipschitzian dynamics for neural net modelling , 1989 .

[3] Erich Harth,et al. Order and chaos in neural systems: An approach to the dynamics of higher brain functions , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[4] M. Zak. Terminal attractors for addressable memory in neural networks , 1988 .

[5] Michail Zak,et al. Terminal attractors in neural networks , 1989, Neural Networks.

[6] Hermann Haken,et al. Information and Self-Organization: A Macroscopic Approach to Complex Systems , 2010 .

[7] V. S. Gurfinkel,et al. REVIEWS OF TOPICAL PROBLEMS: Electrical activity of the brain: Mechanisms and interpretation , 1983 .

[8] Michail Zak. Chaos as a part of logical structure in neurodynamics , 1989 .

[9] Michail Zak,et al. Weakly connected neural nets , 1990 .