Optimization with Neural Networks
in Scientific Applications of Neural Nets, proc. of 194th W.E. Heraeus Seminar (Bad Honnef, Germany, May 11-13, 1998),
eds. J.W. Clark, T. Lindenau and M.L. Ristig,
Lecture Notes in Physics 522, 243-256 (Springer, Berlin 1999)
The recurrent neural network approach to combinatorial optimization has during the last decade evolved into a competitive and versatile heuristic method, that can be used on a wide range of problem types. In the state-of-the-art neural approach the discrete elementary decisions (not necessarily binary) are represented by continuous Potts mean-field neurons, interpolating between the available discrete states, with a dynamics based on iteration of a set of mean-field equations. Driven by annealing in an artificial temperature, they will converge into a candidate solution.
LU TP 98-33