【摘要】 提出用一种基于神经网络的均衡方法,并用误差反向传播(BP)算法对多层前馈网络进行训练。分析和数值仿真结果表明,基于BP网络的频域均衡方法有较好的均衡效果,并且复杂度不高。更多还原

【Abstract】 This paper introduces a novel equalizer based on the neural network. The complex-domain back propagation (BP) algorithm is derived to train the multilayer perceptron. Theoretical analysis and simulation results show that the proposed equalizer based on BP network has better performance than the conventional equalizers.更多还原