Solving TSP by using Lotka-Volterra neural networks

This paper proposes a new approach to solve traveling salesman problem (TSP) by using a class of Lotka-Volterra neural networks (LVNN) with global inhibition. Some stability criteria that ensure the convergence of valid solutions are obtained. It is proved that an equilibrium state is stable if and only if it corresponds to a valid solution of the TSP. Thus, a valid solution can always be obtained whenever the network convergence to a stable state. A set of analytical conditions for optimal settings of LVNN is derived. Simulation results illustrate the theoretical analysis.

[1]  Zhang Yi,et al.  Convergence Analysis of Recurrent Neural Networks , 2003, Network Theory and Applications.

[2]  Zhang Yi,et al.  A columnar competitive model for solving combinatorial optimization problems , 2004, IEEE Transactions on Neural Networks.

[3]  Heiko Wersing.  Learning Lateral Interactions for Feature Binding and Sensory Segmentation , 2001, NIPS.

[4]  Shuzhi Sam Ge,et al.  On parameter settings of Hopfield networks applied to traveling salesman problems , 2005, IEEE Transactions on Circuits and Systems I: Regular Papers.

[5]  Zhang Yi,et al.  Improving local minima of columnar competitive model for TSPs , 2006, IEEE Transactions on Circuits and Systems I: Regular Papers.

[6]  Heiko Wersing,et al.  A Competitive-Layer Model for Feature Binding and Sensory Segmentation , 2001, Neural Computation.

[7]  Satoshi Matsuda,et al.  "Optimal" Hopfield network for combinatorial optimization with linear cost function , 1998, IEEE Trans. Neural Networks.

[8]  Tomoki Fukai,et al.  A subthreshold MOS circuit for the Lotka-Volterra neural network producing the winners-share-all solution , 1999, Neural Networks.

[9]  Tomoki Fukai,et al.  A Simple Neural Network Exhibiting Selective Activation of Neuronal Ensembles: From Winner-Take-All to Winners-Share-All , 1997, Neural Computation.

[10]  K. Tan,et al.  Dynamic stability conditions for Lotka-Volterra recurrent neural networks with delays. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[11]  Mengkang Peng,et al.  An Investigation into the Improvement of Local Minima of the Hopfield Network , 1996, Neural Networks.

[12]  Maria Teresinha Arns Steiner,et al.  A new approach to solve the traveling salesman problem , 2007, Neurocomputing.

[13]  Hidetomo Ichihashi,et al.  A simple steepest descent method for minimizing Hopfield energy to obtain optimal solution of the TSP with reasonable certainty , 1995, Proceedings of ICNN'95 - International Conference on Neural Networks.

[14]  Kay Chen Tan,et al.  An asynchronous recurrent linear threshold network approach to solving the traveling salesman problem , 2008, Neurocomputing.

[15]  Heiko Wersing,et al.  Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions , 2001, Neural Computation.

[16]  Pedro M. Talaván,et al.  Parameter setting of the Hopfield network applied to TSP , 2002, Neural Networks.

[17]  Hiroo Yonezu,et al.  Analog integrated circuits for the Lotka-Volterra competitive neural networks , 1999, IEEE Trans. Neural Networks.

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