【摘要】 对Hopfield神经网络(HNN)模型提出了一个新的能量函数,用以解决多限制路由(MCP)问题。提出利用寻找一个函数的最小问题代替多个约束限制条件,避免了多个限制条件中需要仔细选择多个参数的困难。对6节点和20 节点的计算机模拟表明,采用新的能量函数的HNN的收敛速率在10-3 s量级,考虑到硬件实现,这种神经网络可以用于实时的多限路由选择。更多还原

【Abstract】 A new energy function of Hopfield neural network model is proposed to solve the multi-constrained path problem.Instead of multi-terms corresponding to multi-constraints,just one term is employed in the new energy function.Therefore,the difficulty of choosing a lot of parameters under the multi-constrained conditions in energy is solved.The 6-node and 20-nodes simulation results demonstrate that the proposed algorithm can improve the speed so that the model will converge at its minimum in about 10^-3 seconds.Taking the hardware implemenation into account,such model is suitable for the real world requires.更多还原