AI -- Machine Learning

1. What is Machine Learning

1.1 Artificial Intelligence vs. Machine Learning

1.2 Relations to Other Disciplines 与其他学科的关系

1.3 Human Learning vs. Machine Learning

1.4 What is Skill in Machine Learning 什么是机器学习的技能

1.5 Two General Types of Learning 两种通用的学习类型

1.6 A Formal Definition about Machine Learning 机器学习的形式化定义

1.7 Three Key Elements in the Formal Definition 形式化定义的三要素

2. Three Parties of Machine Learning 机器学习的三个学派

3. Machine Learning Details

3.1 Difficulty in Understanding Machine Learning

3.2 How Machine Learning Works

3.3 Three Perspectives on Machine Learning

3.3.1 Why Three Perspectives

3.3.2 Learning Tasks

3.3.3 Learning Paradigms

3.3.4 Learning Models

4. Applications and Terminologies（术语，名词）

5. Three Perspectives Details

5.1 Tasks in Machine Learning

5.1.1 Classification

• How Classification Works
  
  
  
  
  

• Linear and Nonlinear
  
  
  

• Dimensions and Classes
  
  
  
  

• Applications and Algorithms
  

5.1.2 Regression（回归）

5.1.2.1 How Regression Works

5.1.2.2 Linear and Nonlinear

5.1.2.3 Applications and Algorithms

5.1.3 Clustering

5.1.3.1 How Clustering Works

5.1.3.2 Major Approaches of Clustering

5.1.4 Ranking

5.1.4.1 How Ranking Works

5.1.4.2 Major Approaches of Ranking

5.1.4.3 Applications and Algorithms

5.1.5 Dimensionality Reduction

5.2 Paradigms in Machine Learning

5.2.1 Supervised Learning Paradigm

5.2.1.1 Overview of Supervised Learning

5.2.1.2 Suitable Learning Tasks

5.2.1.3 Formal Description

5.2.1.4 Algorithms of Supervised Learning

5.2.1.5 Applications of Supervised Learning

5.2.1.6 Variants of Supervised Learning

5.2.2 Unsupervised Learning Paradigm

5.2.2.1 Overview

5.2.2.2 Suitable Learning Tasks

5.2.2.3 Algorithms of Unsupervised Learning

5.2.2.4 Applications of Unsupervised Learning

5.2.2.5 How Important Unsupervised Learning

5.2.3 Reinforcement Learning Paradigm

5.2.3.1 Overview of Reinforcement Learning

5.2.3.2 Types of Reinforcement Learning

5.2.3.3 New Algorithms of Reinforcement Learning

5.2.3.4 Applications of Reinforcement Learning

5.2.4 Relations and Other Paradigms

5.2.4 Models in Machine Learning

5.2.4.1 Probabilistic Models

5.2.4.2 Geometric Models

5.2.4.3 Logical Models

5.2.4.4 Networked Models

• Artificial Neural Networks (ANN)
  
  
  
  
  
  
  

• Deep Neural Networks (DNN)