Solving Optimization Problems through Fully Convolutional Networks: an Application to the Travelling Salesman Problem
원문 초록
In the new wave of artificial intelligence, deep learning is impacting various industries. As a closely related area, optimization algorithms greatly contribute to the development of deep learning. But the reverse applications are still insufficient. Is there any efficient way to solve certain optimization problem through deep learning? The key is to convert the optimization to a representation suitable for deep learning. In this paper, a traveling salesman problem (TSP) is studied. Considering that deep learning is good at image processing, an image representation method is proposed to transfer a TSP to an image. Based on samples of a 10 city TSP, a fully convolutional network (FCN) is used to learn the mapping from a feasible region to an optimal solution. The training process is analyzed and interpreted through stages. A visualization method is presented to show how a FCN can understand the training task of a TSP. Once the training is completed, no significant effort is required to solve a new TSP and the prediction is obtained on the scale of milliseconds. The results show good performance in finding the global optimal solution. Moreover, the developed FCN model has been demonstrated on TSP's with different city numbers, proving excellent generalization performance.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Collaborative Problem-Solving in an Optimization Game
Destroy and Repair Using Hyper Graphs for Routing
Blackout DIFUSCO
An Efficient Diffusion-based Non-Autoregressive Solver for Traveling Salesman Problem
DualOpt: A Dual Divide-and-Optimize Algorithm for the Large-scale Traveling Salesman Problem
ELENA: Epigenetic Learning through Evolved Neural Adaptation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.