论文信息 - Minimax and Hamiltonian Dynamics of Excitatory-Inhibitory Networks

Minimax and Hamiltonian Dynamics of Excitatory-Inhibitory Networks

A Lyapunov function for excitatory-inhibitory networks is constructed. The construction assumes symmetric interactions within excitatory and inhibitory populations of neurons, and antisymmetric interactions between populations. The Lyapunov function yields sufficient conditions for the global asymptotic stability of fixed points. If these conditions are violated, limit cycles may be stable. The relations of the Lyapunov function to optimization theory and classical mechanics are revealed by minimax and dissipative Hamiltonian forms of the network dynamics.

[1] B. V. Dean,et al. Studies in Linear and Non-Linear Programming. , 1959 .

[2] B. V. Dean,et al. Studies in Linear and Non-Linear Programming. , 1959 .

[3] Stephen Grossberg,et al. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[4] A. Holden. Competition and cooperation in neural nets , 1983 .

[5] 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.

[6] J. Hopfield,et al. Computing with neural circuits: a model. , 1986, Science.

[7] John C. Platt,et al. Constrained Differential Optimization , 1987, NIPS.

[8] Eric Mjolsness,et al. Algebraic transformations of objective functions , 1990, Neural Networks.

[9] Bard Ermentrout,et al. Complex dynamics in winner-take-all neural nets with slow inhibition , 1992, Neural Networks.

[10] Ibrahim M. Elfadel,et al. Convex Potentials and their Conjugates in Analog Mean-Field Optimization , 1995, Neural Computation.