超限学习机：单隐层的前馈人工神经网络，特别之处在于训练权值的算法: 在单隐层的前馈神经网络中，输入层到隐藏层的权值根据某种分布随机赋予，当我们有了输入层到隐藏层的权值之后，可以根据最小二乘法得到隐藏层到输出层的权值-Overrun learning machine: feed-forward artificial neural network single hidden layer, is unique in that algorithm training weights: Before a s

Classification, Regression

该方法随机给定神经元权值中的输入权值和阈值，然后通过正则化原则计算输出权值，神经网络依然能逼近任意连续系统。(The method gives the input weights and thresholds of neuron weights randomly, and then calculates the output weights by regularization principle. The neural network can still approximate any cont