This paper deals with a neural network model in which each neuron performs a threshold logic function. An important property of the model is that it always converges to a stable state when operating in a serial mode [2,5]. This property is the basis of the potential applications of the model such as associative memory devices and combinatorial optimization [3,6].
One of the motivations for use of the model for solving hard combinatorial problems is the fact that it can be implemented by optical devices and thus operate at a higher speed than conventional electronics.
The main theme in this work is to investigate the power of the model for solving NP-hard problems [4,8], and to understand the relation between speed of operation and the size of a neural network. In particular, it will be shown that for any NP-hard problem the existence of a polynomial size network that solves it implies that NP=co-NP. Also, for Traveling Salesman Problem (TSP), even a polynomial size network that gets an e-approximate solution does not exist unless P=NP.
The above results are of great practical interest, because right now it is possible to build neural networks which will operate fast but are limited in the number of neurons.
[1]
Jehoshua Bruck,et al.
A study on neural networks
,
1988,
Int. J. Intell. Syst..
[2]
Y S Abu-Mostafa,et al.
Neural networks for computing
,
1987
.
[3]
H. D. Ratliff,et al.
Minimum cuts and related problems
,
1975,
Networks.
[4]
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.
[5]
Kenneth Steiglitz,et al.
On the Complexity of Local Search for the Traveling Salesman Problem
,
1977,
SIAM J. Comput..
[6]
Joseph W. Goodman,et al.
A generalized convergence theorem for neural networks
,
1988,
IEEE Trans. Inf. Theory.
[7]
Kenneth Steiglitz,et al.
Combinatorial Optimization: Algorithms and Complexity
,
1981
.
[8]
David S. Johnson,et al.
Computers and Intractability: A Guide to the Theory of NP-Completeness
,
1978
.