论文信息 - Computer aided investigations of artificial neural systems

Computer aided investigations of artificial neural systems

An attempt is made to demonstrate how symbolic computation can be applied to aid in the analysis and derivation of neural systems. The authors review the general method and techniques of the Lyapunov method for the stability analysis of artificial neural systems. They present some strategies for using computer algebra systems and their extensions to analyze the stability of known neural systems and to derive novel stable ones. A brief description of a toolkit developed in MACSYMA is also provided. An illustration is given to sketch the derivation of neural learning dynamics by the toolkit. A discussion of future developments is included.<<ETX>>

B. Schurmann | D. Wang

[1] U. Ramacher,et al. Adaptive recurrent neural networks and dynamic stability , 1990 .

[2] C. Lee Giles,et al. Encoding Geometric Invariances in Higher-Order Neural Networks , 1987, NIPS.

[3] J J Hopfield,et al. Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[4] Stephen Grossberg,et al. Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[5] Schürmann. Stability and adaptation in artificial neural systems. , 1989, Physical review. A, General physics.

[6] Barak A. Pearlmutter. Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[7] Dongming Wang,et al. Stable Neurodynamics and Symbolic Computation , 1990 .

[8] Amir F. Atiya. Learning on a General Network , 1987, NIPS.

[10] B Kosko,et al. Adaptive bidirectional associative memories. , 1987, Applied optics.

[11] Dongming Wang. A toolkit for manipulating indefinite summations with application to neural networks , 1991, ISSAC '91.