Abstract
The Maximum Clique Problem (MCP) is a classic combinatorial optimization problem in graph theory. Its deterministic algorithms include back tracking, branch and bound methods, etc. With the increase of the dimension of the maximum clique problem, the solution time increases greatly until it cannot be solved. In this paper, the neural networks combined with a deterministic algorithm trained by supervised learning are used to solve the MCP. The optimal solution obtained by the network is selected by Back Tracking Method (BA), which not only reduces the solving time, but also ensures the accuracy of the solution. The experimental results show that the pointer network under supervised learning training has higher accuracy and more stable results in solving MCP.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
