In this paper, the authors focus on swarm intelligence represented by the ant colony system and artificial neural network simulating the brain working principles, and analyse the similarities between them by the approaches of a complexity study. Firstly, the similarities between swarm intelligence and neural network have been analysed qualitatively from system structure and operation mechanisms and the results show that there exist obvious similarities in overall disciplines between them. Moreover, the mapping relationships between swarm intelligence and artificial neural network at algorithm level have been revealed using the travelling salesman problem (TSP), which illustrates that these two algorithms are also similar from the viewpoint of numeric computing and simulating when they are directly used to solve a complex problem. In addition, the swarm intelligence algorithm and the artificial neural network algorithm are adopted to solve an engineering practical problem, which can be transformed into the TSP. The results show that the performance of these two algorithms still has close similarities. The purpose of the above work is to construct the inherent relationship among different bio-inspired computation methods, which has both important theoretic significance and practical value to reveal the generation and operation mechanisms of human intelligence.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.