Linear programming and simple associative memories

摘要

Many optimization procedures presume the availability of an initial approximation in the neighborhood of a local or global optimum. Unfortunately, finding a set of good starting conditions is itself nontrivial. We describe a procedure for identifying approximate solutions to constrained optimization problems. Simple associative memories are trained to map the inputs of closely related linear programs to optimal solution vectors. The procedure performs well, identifying good heuristic solutions for representative examples. Modest infeasibilities exist in these estimated solutions, but the basic variables associated with true optimums are readily apparent.