论文信息 - Generalized maximum-flow solution based on CNN circuit analysis

Generalized maximum-flow solution based on CNN circuit analysis

In our previous research, the Maximum-Flow Neural Network (MF-NN) was proposed, and we showed that the MF-NN is possible to solve any maximum-flow problems. However, the MF-NN has problems of convergence of sigmoidal function. In this research, we propose novel MF-NN using piecewise linear function for improving those problems. Moreover, this novel method is possible to considerably reduce a calculation cost.

M. Sato | M. Tanaka

[1] Ravindra K. Ahuja,et al. Network Flows: Theory, Algorithms, and Applications , 1993 .

[2] D. R. Fulkerson,et al. A Simple Algorithm for Finding Maximal Network Flows and an Application to the Hitchcock Problem , 1957, Canadian Journal of Mathematics.

[3] Andrew V. Goldberg,et al. On Implementing the Push—Relabel Method for the Maximum Flow Problem , 1997, Algorithmica.

[4] John J. Hopfield,et al. Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit , 1986 .

[5] Rudolf Ahlswede,et al. Network information flow , 2000, IEEE Trans. Inf. Theory.

[6] Andrew V. Goldberg,et al. A new approach to the maximum flow problem , 1986, STOC '86.

[7] Vijaya Ramachandran,et al. The complexity of minimum cut and maximum flow problems in an acyclic network , 1987, Networks.

[8] Mamoru Tanaka,et al. Maximum-Flow Neural Network: A Novel Neural Network for the Maximum Flow Problem , 2009, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[9] D. R. Fulkerson,et al. Maximal Flow Through a Network , 1956 .

[10] J. J. Hopfield,et al. “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.