To search, Click below search items.


All Published Papers Search Service


Design and Analysis of Positively Self-Feedbacked Hopfield Neural Network for Crossbar Switching


Yalan Zhou, Jiahai Wang, Jian Yin


Vol. 7  No. 5  pp. 65-70


After the original work of Hopfield and Tank, a lot of modified Hopfield neural network models have been proposed for combinatorial optimization problems. Recently, a positively self-feedbacked Hopfield neural network architecture was proposed by Li et al. and successfully applied to crossbar switching problem. In this paper, we analysis the dynamics of the positively self-feedbacked Hopfield neural network, then show the role of the self-feedback and point out where the good performance comes from. Based on the theoretical analysis, we get better simulation results for crossbar switching problem by selecting suitably positive self-feedback value of the network.


positively self-feedbacked Hopfield neural network, crossbar switching problem, combinatorial optimization problems