递归神经网络的并行LM算法

A Parallel LM Algorithm for Recurrent Neural Network

针对递归神经网络BP学习算法收敛慢的缺陷,将Levenberg-Marquardt(LM)算法引入到递归神经网络权值的训练,为了克服LM算法集中运算的不足,设计出完整的并行LM算法。该算法将计算分配到神经网络中的每个神经元,符合神经网络的并行结构特点。仿真结果表明,该算法比传统BP算法具有更好的收敛性,且比LM算法大大节省了计算时间。

A new recursive learning algorithm of diagonal recurrent neural was proposed by introducing Levenberg-Marquardt（LM） algorithm, which overcome the slow convergence of BP algorithm. In order to overcome the disadvantage of the centralized computing of LM algorithm, a parallel LM algorithm is derived. In the new parallel algorithm, the computation is distributed to each neuron in the network, which gives prominence to the nature of parallel handling information of the neural network. Simulation results show that the proposed algorithm converges faster than the traditional recurrent BP algorithm, and saves lots of computational time compared with LM centralized computing algorithm.