机器学习介绍
![在这里插入图片描述](https://img-blog.csdnimg.cn/9a58f6d41cac4d3bab111dc82bff1363.png?x-oss-process=image/watermark,type_d3F5LXplbmhlaQ,shadow_50,text_Q1NETiBAQWlydnZ5,size_20,color_FFFFFF,t_70,g_se,x_16#pic_center)
What is Machine Learning
Machine Learning ≈ Looking for a Function From Data
-
Speech Recognition
-
Image Recognition
-
Playing Go
-
Dialogue System
Framework
Training
-
Define a set of function(Model)
-
Goodness of function f(Training Data: function input、function output)
Pick the “Best” Function f ∗ f^{\ast} f∗
Testing
- Using f ∗ f^{\ast} f∗ test
Learning Map
Task
Regression
The output of the target function f is “scalar”
Classification
-
Binary Classification
I n p u t → F u n c t i o n f Y e s o r N o Input\xrightarrow{Function\,\,f}Yes\,\,or\,\,No InputFunctionfYesorNo
-
Multi-class Classification
I n p u t → F u n c t i o n f C l a s s 1 , C l a s s 2 , . . . C l a s s N Input\xrightarrow{Function\,\,f}Class1, Class2, ... Class\,\,N InputFunctionfClass1,Class2,...ClassN
Model
Supervised Learning
-
Linear Model
-
Deep Learning
Semi-supervised Learning
Transfer Learning
Unsupervised Learning
Stuctured Learning
Beyond Classification
Reinforcement Learning
Learning from critics