Answers are grounded in this paper and cite their sources.
The linear programming network of Tank and Hopfield is shown to obey the same unifying stationary cocontent theorem as the canonical nonlinear programming circuit of Chua and Lin. Application of this theorem highlights an error in the design of Tank and Hopfield and suggests how this can be corrected to guarantee the existence of a bounded solution. The accuracy of the solution is maximized when the circuit of Tank and Hopfield reduces to the simplest special case of the canonical nonlinear programming circuit.
No takes yet. Share an insight, caveat, or question.
Kennedy et al. (1987) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: