On the Convergence and Parameter Relation of Discrete-Time Continuous-State Hop field Networks with Self-Interaction Neurons

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, a discrete-time convergence theorem for continuous-state Hopfield networks with self-interaction neurons is proposed. This theorem differs from the previous work by Wane in that the original updating rule is maintained while the network is still guaranteed to monotonically decrease to a stable state. The relationship between the parameters in a typical class of energy functions is also investigated, and consequently a "guided trial-and-error" technique is proposed to determine the parameter values. The third problem discussed in this paper is the post-processing of outputs, which turns out to be rather important even though it never attracts enough attention. The effectiveness of all the theorems and post-processing methods proposed in this paper is demonstrated by a large number of computer simulations on the assignment problem and the N-queen problem of different sizes.

• 社団法人電子情報通信学会の論文
• 2001-12-01

著者

• Feng G

  Nanyang Technological Univ. Singapore

• Douligeris C

  Univ. Piraeus Piraeus Grc

• FENG Gang

  the Department of Electrical and Computer Engineering, University of Miami

• DOULIGERIS Christos

  the Department of Informatics, University of Piraeus

関連論文

• Heuristic and Exact Algorithms for QoS Routing with Multiple Constraints(Regular section)
• Linear and Nonlinear Lagrange Relaxation Algorithms for Delay-Constrained Least-Cost QoS Routing(Regular Section)
• On the Convergence and Parameter Relation of Discrete-Time Continuous-State Hop field Networks with Self-Interaction Neurons

スポンサーリンク