Problem Detail: I was curious if there were any new developments in solving the traveling salesman problem using something like a Hopfield recurrent neural network. I feel like I saw something about recent research getting a breakthrough in this, but I can’t find the academic papers anywhere. Is anyone aware of any new, novel developments in this area?
Asked By : Rob
Answered By : vzn
there are many papers on using artificial neural networks to solve TSP including recurrent and Hopfield networks, and they “succeed” in a rough sense, but so far there does not seem to be any evidence that the techniques are in any way (strongly?) superior to other algorithmic approaches, so its something more like a research curiosity at the moment. the use of ANNs for this problem is indeed counterintuitive from the pov of combinatorial algorithmics and the mechanisms by which the problem inputs/ outputs are encoded are novel and tend to vary, and maybe are not yet so standardized. the authors seem maybe more interested in demonstrating “proof of concept” and a comparison with other algorithm types seems more rare (there is some in the last paper). see eg
- Traveling salesman problem using neural network techniques / Abdel-Moetty
- Using Hopfield Networks to Solve Traveling Salesman Problems Based on Stable State Analysis Technique / Feng, Douligeris
- Comparison of Neural Networks for Solving the Travelling Salesman Problem / La Maire, Mladenov
- A Recurrent Neural Network to Traveling Salesman Problem / Siqueira, Scheer, Steiner
Best Answer from StackOverflow
Question Source : http://cs.stackexchange.com/questions/54200
