机器学习是一个令人兴奋的话题，关于设计可以从数据中学习的机器。本课程涵盖了机器学习的必要理论、原理和算法。这些方法是基于统计学和概率论的——它们现在已经成为设计显示人工智能的系统的必要条件。
Introduction
Machine Learning-Overview(28MB) Video
Python and ML Frameworks(13.9MB) Video
Linear Algebra(4.5MB) Video: Part 1 Part 2
Example: Curve Fitting(934KB) Video
Probability Theory(3.5MB)
Numerical Computation(1.4MB)
Decision-Theory(488KB)
Information Theory(715KB)
Probability Distributions
Discrete Distributions(1MB)
Gaussian Distribution(833KB)
Gaussian Bayesian Networks(738KB)
Linear Models for Regression
Regression with Basis Functions(7.3MB) Video
Gradient Descent(3.2MB) Video
Bias-Variance(950KB)
Bayesian Regression(2.5MB)
Bayesian Model Comparison(478KB)
Evidence Approximation(746KB)
Example: Computer Science Ranking(126KB)
Linear Models for Classification
Fixed Basis Functions(254KB)
Logistic Regression(3.6MB)
Iterative Reweighted Least Squares(5.1MB) Video
Multiclass Logistic Regression(4.6MB)
Probit Regression(356KB)
Canonical Link Functions(263KB)
Overview(4.6MB) Video
Discriminant Functions(5MB) Video
Probabilistic Generative Models(1.3MB) Video
Probabilistic Discriminative Models
Laplace Approximation (1.3MB)
Bayesian Logistic Regression(1.1MB) Video
Variational Bayesian Logistic Regression(3.3MB) Video
Neural Networks
Norm Penalty: Bayesian Interpretation(1.2MB) Video
Convolutional Networks(4.9MB) Video
Soft Weight Sharing(1.2MB)
Biology(4.5MB) Video
Feed-forward Network Functions(5.3MB) Video
Network Training(2.6MB) Video
Backpropagation(8.7MB) Video
The Hessian Matrix(562KB)
Regularization in Neural Networks
Mixture Density Networks (634KB)
Bayesian Neural Networks(716KB)
Deep Learning Overview(5.2MB)
See course on Deep Learning
Kernel Methods
Kernel Methods(6.3MB)
Radial Basis Function Networks(812KB)
Gaussian Processes(6.8MB)
Sparse Kernel Machines
Support Vector Machines(5.4MB)
SVM for Overlapping Distributions(1.3MB)
Multiclass SVMs (1.4MB)
Relation to Logistic Regression (446KB)
Probabilistic Graphical Models
See Course on Probabilistic Graphical Models
Mixture Models and EM
Unsupervised Learning(1.9MB) Video
K-means Clustering(1.4MB) Video
Gaussian Mixture Models(1.5MB)
Latent Variable View of EM(1.1MB)
Bernoulli Mixture Models(3.1MB)
Theoretical Basis of EM(693KB)
Approximate Inference
Approximate Inference(180KB)
Variational Inference(3.3MB)
Variational Mixture of Gaussians(1MB)
Sampling Methods
Need for Sampling (6.6MB)
Basic Sampling Methods(2.5MB)
Markov Chain Monte Carlo Sampling(815KB)
Gibbs Sampling(1.2MB)
Continuous Latent Variables
Principal Components Analysis
See Section 3.2 of course on Data Mining
Nonlinear Latent Variable Models
Sequential Data
Maximum Likelihood for the HMM(8.5MB)
The forward-backward algorithm(15.9MB)
Extensions to HMMs
(287KB)
Markov Models(2.5MB)
Hidden Markov Models(3.1MB)
Linear Dynamical Systems(217KB)
Conditional Random Fields(1.6MB)
Combining Models
Decision Trees(pdf, 1.9MB)
Learning Trees(pdf, 596KB)
Combining Models(pdf, 1.7MB)
Bagging(pdf, 675KB)
Boosting(pdf, 1.1MB)
Tree Models
Random Forests(pdf, 3.4MB)
Reinforcement Learning
Reinforcement Learning Overview(pdf 4MB) Video
The Learning Task (pdf 1MB)
Q-Learning (pdf 6MB)
Nondeterministic Q-Learning (pdf 4.9MB)
Deep Reinforcement Learning (pdf 3.5MB)
Ethics of AI
Ethics(pdf 8.8MB) Video
Trustworthy AI
Explanation by Example(pdf 3.4MB)
Deep Explanation(pdf 14.6MB)
Causal Explanation(pdf 16.4MB)
Trustworthy AI(pdf 2.9MB)
Explainable AI(pdf 24MB)
Concept Learning
Hypothesis Space (pdf, 111KB)
Candidate Elimination (pdf,236KB)
Computational Learning Theory
PAC Learning(pdf, 98KB)
VC Dimension(pdf, 321KB)
Mistake Bound(pdf, 51KB)
专知便捷查看
便捷下载，请关注专知人工智能公众号（点击上方蓝色专知关注）
专知，专业可信的人工智能知识分发，让认知协作更快更好！欢迎注册登录专知www.zhuanzhi.ai，获取5000+AI主题干货知识资料！点击“阅读原文”，了解使用专知，查看获取5000+AI主题知识资源
