关键词: BP算法, Levenberg-Marquardt算法, 上下三角(Lu)分解, Marquardt灵敏度矩阵

Abstract:

The improved version of BP(Back Propagation)algorithm with the fastest convergence speed,LMBP (Levenberg-Marquardt BP)algorithm,is investigated,finding out the bottlenecks of the convergence speed,that is,the initialization of iteration controlling parameters has a great influence on the iterated number.the calculation of the inverse matrix involved in each iteration is the most time-consuming ,and it will take long to carry out a certain interation if the sum of squared el'TOrs in each interation is not decreased.To solve these problems,LU(Lower-Upper)decomposition is employed to avoid the time-consuming calculation of inverse matrix.and the one-di-mension searching is adopted to accelerate the decrease of the object function.Thus,a quick BP neurM network al-gorithm named QLMBP(Quick LMBP)is proposed.The proposed QLMBP algorithm is independent on the itera tion controlling parameters and its convergence speed is about 100 times that of the LMBP algorithm convergence speed.

Key words: Palgorithm, Levenberg-Marquardt algorithm, LU(Lower-Upper)decomposition, Marquardt sensi-tivity matrix