Massively parallel analog tabu search using neural networks applied to simple plant location problems

Simple plant location problems (SPLP) were solved using Tabu Neural Network (TANN), which is an analog, global search model that is easily implemented in massively parallel hardware. The results showed that the TANN outperforms by an average of 85% the Hopfield-Tank neural network The TANN was designed to handle combinatorial optimization problems by integrating the tabu search metaheuristic and neural networks into a single architecture.