參考內(nèi)容:
斯坦福大學公開課 :機器學習課程
Stanford-CS-229-CN
Video 1 機器學習的動機與應(yīng)用
一犁嗅、Supervised Learning
1. Regression problems
如房價預(yù)測
2. Classification problems
如腫瘤是否良性
二究珊、Learning Theory
三号显、Unsupervised Learning
如分隔兩個聲源的聲音
四耻涛、Reinforcement Learning(強化學習)
1. reward function
如控制飛機自動飛行,bad dog & good dog example
Video 2 監(jiān)督學習應(yīng)用.梯度下降
一为严、Supervised Learning
1. Regression problem:
自動駕駛:人類司機教算法學習駕駛
房價預(yù)測:
- m = # training examples
- x = "input" variables/features
- y = "output" variables/ "target" variables
- (x, y) = training example
- ith training example = (x(i), y(i))
假設(shè)X1 = Size球榆,X2 = # the rooms,
h(x) = hθ(x) = θ0 + θ1x1 + θ2x2
-
隨機梯度下降 stochastic gradient descent (incremental DG) 在有大規(guī)模數(shù)據(jù)集時下降更快菇民,在最小值附近徘徊尽楔。