摘要：
1. 基本形式 f(æ) = ω1 X1 + ω2 X2 十...+ωdXd + b , 2.线性回归 均方误差有非常好的几何意义--它对应了常用的欧几里得距离或简称"欧 氏距离" (Euclidean distance). 基于均方误差最小化来进行模型求解的方法称为"最小二乘法" (least s 阅读全文
摘要：
对于overfitting常用regularization正则化 参见machine learning Regularization is designed to address the problem of overfitting. There are two main options to ad 阅读全文