A recurrent neural network for solving bilevel linear programming problem.

abstract

• In this brief, based on the method of penalty functions, a recurrent neural network (NN) modeled by means of a differential inclusion is proposed for solving the bilevel linear programming problem (BLPP). Compared with the existing NNs for BLPP, the model has the least number of state variables and simple structure. Using nonsmooth analysis, the theory of differential inclusions, and Lyapunov-like method, the equilibrium point sequence of the proposed NNs can approximately converge to an optimal solution of BLPP under certain conditions. Finally, the numerical simulations of a supply chain distribution model have shown excellent performance of the proposed recurrent NNs.

authors

• Huang, Tingwen

published proceedings

• IEEE Trans Neural Netw Learn Syst

author list (cited authors)

• He, X., Li, C., Huang, T., Li, C., & Huang, J.

citation count

• 113

complete list of authors

• He, Xing||Li, Chuandong||Huang, Tingwen||Li, Chaojie||Huang, Junjian

publication date

• April 2014

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• IEEE Transactions on Neural Networks and Learning Systems  Journal

keywords

• Algorithms
• Computer Simulation
• Feedback
• Models, Theoretical
• Neural Networks, Computer
• Pattern Recognition, Automated
• Programming, Linear

Digital Object Identifier (DOI)

• 10.1109/TNNLS.2013.2280905

start page

• 824

end page

• 830

volume

• 25

issue

• 4

URL

• http://dx.doi.org/10.1109/tnnls.2013.2280905