通过反复训练模板能有较高的识别率，BP神经网络用于函数拟合与模式识别，采用加权网络中节点强度和权重都是幂率分布的模型，gmcalab 快速广义的形态分量分析，本科毕设要求参见标准测试模型，用MATLAB实现的压缩传感。- Through repeated training UqxYzxdlate have higher recognition rate, BP neural network function fitting and pattern recognition, Using weighted model nodes in the network strength and weight are power law distribution, gmcalab fast generalized form component analysis, Undergraduate complete set requirements refer to the standard test models, Using MATLAB compressed sensing.