Self-adaptive autowave pulse-coupled neural network for shortest-path problem

• Published in: Neurocomputing (Amsterdam) Vol. 115; pp. 63 - 71
• Main Authors: Li, Xiaojun, Ma, Yide, Feng, Xiaowen
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 04.09.2013; Elsevier
• Subjects: Applied sciences; Artificial intelligence; Autowave; Computer science; control theory; systems; Connectionism. Neural networks; Exact sciences and technology; Information retrieval. Graph; Pattern recognition. Digital image processing. Computational geometry; Pulse-coupled neural network; Self-adaptive autowave PCNN; Shortest path; Theoretical computing; Shortest path; Autowave; Pulse-coupled neural network; Self-adaptive autowave PCNN; Computer vision; Information system; Adaptability; Routing; Neural network; Modeling
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2012.12.030

Pulse Coupled Neural Network (PCNN) is suitable for dealing with the classical shortest path problem, because of its autowave characteristic. However, most methods suggest that the autowave of PCNN models should keep a constant speed in finding the shortest paths. This paper proposes a novel self-adaptive autowave pulse-coupled neural network (SAPCNN) model for the shortest path problem. The autowave generated by SAPCNN propagates adaptively according to the current network state, which guarantees it spreads more effectively in finding the shortest paths. Our experiments, which have been carried out for both the shortest paths problem and K shortest paths problem, show that our proposed algorithm outperforms classical algorithms.