A Neural Network Model Based on Differential Evolution Algorithm for Traveling Salesman Problem

This paper presents a novel neural network-based optimization framework, NNDE, to solve the traveling salesman problem (TSP). The core idea is to use a radial basis function network (RBFN) to evaluate each edge by its three features, thereby guiding a modified nearest neighbor algorithm (MNNA) in constructing satisfactory solutions. Then, the differential evolution (DE) algorithm is employed to iteratively optimize the network parameters to enhance the performance of RBFN. Finally, the proposed NNDE is evaluated on several benchmark instances of TSP. The experimental results demonstrate its performance and feasibility.