针对标准 算法存在的缺陷，本文给出了基于matlab语言的神经网络几种改进的算法- 阐述了各种算法的优化技术原理、优缺点，并就它们的训练速度和内存消耗情况作了比较-According to the defects of standard algorithm, this paper presents the neural network based on matlab language several improvement algorithm, expounds the optimization of the algorithm of technical principle, advantages and disadvantages, and their training speed and memory consumption compared