林轩田机器学习基石(国语)
https://www.youtube.com/playlist?list=PLXVfgk9fNX2I7tB6oIINGBmW50rrmFTqf
Machine Learning Foundations (機器學習基石)
视频选集
（8/65）
1.1 The Learning Problem - Course Introduction
09:50
1.2 The Learning Problem - What Is Machine Learning
18:30
1.3 The Learning Problem - Applications of Machine Learning
18:58
1.4 The Learning Problem - Components of Learning
11:46
1.5 The Learning Problem - Machine Learning and Other Fields
10:22
2.1 Learning to Answer Yes_No - Perceptron Hypothesis Set
15:12
2.2 Learning to Answer Yes_No - Perceptron Learning Algorithm
19:47
2.3 Learning to Answer Yes_No - Guarantee of PLA
12:38
2.4 Learning to Answer Yes_No - Non-Separable Data
12:56
3.1 Types of Learning - Learning with Different Output Space
16:57
3.2 Types of Learning - Learning with Different Data Label
18:14
3.3 Types of Learning - Learning with Different Protocol
11:10
3.4 Types of Learning - Learning with Different Input Space
14:14
4.1 Feasibility of Learning - Learning is Impossible
13:03
4.2 Feasibility of Learning - Probability to the Rescue
11:33
4.3 Feasibility of Learning - Connection to Learning
16:47
4.4 Feasibility of Learning - Connection to Real Learning
18:07
5.1 Training versus Testing - Recap and Preview
13:19
5.2 Training versus Testing - Effective Number of Lines
15:27
5.3 Training versus Testing - Effective Number of Hypotheses
16:18
5.4 Training versus Testing - Break Point
07:44
6.1 Theory of Generalization - Restriction of Break Point
13:47
6.2 Theory of Generalization - Bounding Function - Basic Cases
06:57
6.3 Theory of Generalization - Bounding Function - Inductive
14:48
6.4 Theory of Generalization - A Pictorial Proof
16:02
7.1 The VC Dimension - Definition of VC Dimension
12:34
7.2 The VC Dimension - VC Dimension of Perceptrons
13:28
7.3 The VC Dimension - Physical Intuition of VC Dimension
06:11
7.4 The VC Dimension - Interpreting VC Dimension
17:14
8.1 Noise and Error - Noise and Probabilistic Target
16:30
8.2 Noise and Error - Error Measure
15:11
8.3 Noise and Error - Algorithmic Error Measure
13:48
8.4 Noise and Error - Weighted Classification
16:55
9.1 Linear Regression - Linear Regression Problem
09:37
9.2 Linear Regression - Linear Regression Algorithm
20:04
9.3 Linear Regression - Generalization Issue
20:35
9.4 Linear Regression - for Binary Classification
11:24
10.1 Logistic Regression - Logistic Regression Problem
14:02
10.2 Logistic Regression - Logistic Regression Error
15:59
10.3 Logistic Regression - Gradient of Logistic Regression Error
15:39
10.4 Logistic Regression - Gradient Descent
19:19
11.1 Linear Models for Classification - Binary Classification
20:59
11.2 Linear Models for Classification - Stochastic Grad. Descent
11:40
11.3 Linear Models for Classification - Multiclass via Logistic
14:19
11.4 Linear Models for Classification - Multiclass via Binary
11:36
12.1 Nonlinear Transformation - Quadratic Hypotheses
23:21
12.2 Nonlinear Transformation - Nonlinear Transform
09:53
12.3 Nonlinear Transformation - Price of Nonlinear Transform
15:38
12.4 Nonlinear Transformation - Structured Hypothesis Sets
09:37
13.1 Hazard of Overfitting - What is Overfitting
10:19
13.2 Hazard of Overfitting - The Role of Noise and Data Size
13:36
13.3 Hazard of Overfitting - Deterministic Noise
14:08
13.4 Hazard of Overfitting - Dealing with Overfitting
10:50
14.1 Regularization - Regularized Hypothesis Set
18:45
14.2 Regularization - Weight Decay Regularization
24:09
14.3 Regularization - Regularization and VC Theory
08:16
14.4 Regularization - General Regularizers
13:29
15.1 Validation - Model Selection Problem
15:34
15.2 Validation - Validation
13:25
15.3 Validation - Leave-One-Out Cross Validation
16:07
15.4 Validation - V-Fold Cross Validation
10:42
16.1 Three Learning Principles - Occam's Razor
09:37
16.2 Three Learning Principles - Sampling Bias
11:51
16.3 Three Learning Principles - Data Snooping
12:29
16.4 Three Learning Principles - Power of Three
08:50
顶部