![](https://img-blog.csdnimg.cn/20201014180756927.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
浅层学习
文章平均质量分 89
weitian_bnu
机器学习算法爱好者,现就职于国内一家主流互联网公司。个人研究兴趣:深度学习,机器学习理论等。
展开
-
CS229 Lecture Note(1): Linear Regression
1. LMS AlgorithmThe Ordinary Least Squares Regression Model: h(θ)=θTxh(\theta)=\theta^TxCost Function: J(θ)=12∑mi=1(hθ(xi)−yi)2J(\theta)=\frac{1}{2}\sum_{i=1}^m(h_\theta(x^i)-y^i)^2LMS (least mean s原创 2016-04-12 13:33:55 · 395 阅读 · 0 评论 -
CS229 Lecture Notes(2): Logistic Regression
Logistic RegressionBinary classification problemFailure of OLS regression in binary classification problem:hard to define the thresholdno sense if y>1y>1 or y<0y<0Hypothesis: hθ(x)=g(θTx)=11+e−θTxh原创 2016-04-18 14:26:26 · 245 阅读 · 0 评论 -
CS229 Lecture Notes(3): Generalized Linear Models
The exponential familyA class of distributions is in the exponential family if it can be written in the from p(y,η)=b(y)exp(ηTT(y)−a(η))p(y,\eta)=b(y)exp(\eta^TT(y)-a(\eta)) where:η\eta: the natural原创 2016-04-18 14:27:55 · 330 阅读 · 0 评论 -
CS229 Lecture Notes(4): Generative Learning Algorithm
Generative Learning Algorithmdiscriminative learning algorithm: Algorithms try to learn p(y|x)p(y|x) directly or try to learn mappings f(x)f(x) directly from the space of inputs \mathcal{X} to the la原创 2016-04-18 14:29:05 · 229 阅读 · 0 评论