Neural network solutions to a graph theoretic problem

A Hopfield-model-based solution to the node covering problem is considered. It is shown that the sequential algorithm is always convergent, and that for an n-node graph, this convergence occurs in no more than 2n iterations. For the parallel algorithm, a resetting scheme guaranteeing convergence is proposed. Detailed analyses of both schemes are given.<<ETX>>

[1]  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.

[2]  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.

[3]  D Psaltis,et al.  Optical implementation of the Hopfield model. , 1985, Applied optics.

[4]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[5]  Joseph W. Goodman,et al.  A generalized convergence theorem for neural networks , 1988, IEEE Trans. Inf. Theory.

[6]  Pinaki Mazumder,et al.  Neural computing for built-in self-repair of embedded memory arrays , 1989, [1989] The Nineteenth International Symposium on Fault-Tolerant Computing. Digest of Papers.

[7]  Jehoshua Bruck,et al.  Neural networks, error-correcting codes, and polynomials over the binary n -cube , 1989, IEEE Trans. Inf. Theory.