机器学习介绍
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
2530
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
