A study of the asymptotic behavior of neural networks

The stability properties are studied of neural networks modeled as a set of nonlinear differential equations of the form TX+X=Wf(X)+b where X is the neural membrane potential vector, W is the network connectivity matrix, and F(X) is the nonlinearity (an essentially sigmoid function). Topologies of neural networks that exhibit asymptotic behavior are established. This behavior depends solely on the topology of the network. Moreover, the connectivity W need not be symmetric. Networks topologically similar to the cerebellum fall in this category and exhibit asymptotic behavior. The simulated behavior of typical neural networks is presented. >

[1]  D. Marr.  A theory of cerebellar cortex , 1969, The Journal of physiology.

[2]  P. Andersen.  Organization of Hippocampal Neurons and Their Interconnections , 1975 .

[3]  Structures of Excitation and Inhibition , 1978 .

[4]  R.W. Newcomb,et al.  Hysteretic system for neural-type circuits , 1981, Proceedings of the IEEE.

[5]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[6]  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.

[7]  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.

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

[9]  Demetri Psaltis,et al.  Optical Neural Computers , 1987, Topical Meeting on Optical Computing.

[10]  A. P. Thakoor,et al.  A neurocomputer based on an analog-digital hybrid architecture , 1987 .

[11]  Carver Mead,et al.  Silicon Models of Neural Computation , 1989 .