极限学习机（Extreme Learning Machine, ELM）用来训练单隐藏层前馈神经网络（SLFN）与传统的SLFN训练算法不同，极限学习机随机选取输入层权重和隐藏层偏置，输出层权重通过激活函数函数，依据Moore-Penrose（MP）广义逆矩阵理论计算解析求出。(Extreme learning machine (ELM) is used to train single hidden layer feedforward neural network (SLFN). Different from traditional SLFN training algorithm, elm randomly selects input layer weight and hidden layer bias, and output layer weight is calculated and analyzed according to Moore Penrose (MP) generalized inverse matrix theory through activation function function function.)