This structure and all of this original content is the work of Prof. Andrew Ng of Stanford University, Co-founder of Coursera
You can learn by yourself at Machine Learning Course at Coursera
Cấu trúc và các nội dung gốc của tất cả các bài viết dưới đây do giáo sư Andrew Ng xây dựng. Ông là giáo sư của đại học Stanford, đồng sáng lập Coursera
Bạn có thể tự học khóa Machine Learning tại Machine Learning Course at Coursera
1. Part 1: Introduction
2. Part 2: Linear Regression with Multiple Variables
2.4. Submitting Programming Assignments
2.5. Octave/Matlab Tutorial
3. Part 3: Logistic Regression
3.1. Classification and Representation
3.2. Logistic Regression Model
3.3. Multiclass Classification
3.4. Solving the Problem of Overfitting
4. Part 4: Neural Networks: Representation
4.1. Motivations
4.2. Neural Networks
4.3. Applications
5. Part 5: Neural Networks: Learning
5.1. Cost Function and Backpropagation
5.2. Backpropagation in Practice
5.3. Application of Neural Networks
6. Part 6: Advice for Applying Machine Learning
6.1. Evaluating a Learning Algorithm
6.2. Bias vs. Variance
6.3. Machine Learning System Design
6.4. Building a Spam Classifier
6.5. Handling Skewed Data
6.6. Using Large Data Sets
7. Part 7: Support Vector Machines
7.1. Large Margin Classification
7.2. Kernels
7.3. SVMs in Practice
8. Part 8: Unsupervised Learning
8.1. Clustering
8.2. Dimensionality Reduction
8.3. Motivation
8.4. Principal Component Analysis
8.5. Applying PCA
9. Part 9: Anomaly Detection
9.1. Density Estimation
9.2. Building an Anomaly Detection System
9.3. Multivariate Gaussian Distribution (Optional)
9.4. Predicting Movie Ratings
9.5. Collaborative Filtering
9.6. Low Rank Matrix Factorization
10. Part 10: Large Scale Machine Learning
10.1. Gradient Descent with Large Datasets
10.2. Advanced Topics
11. Part 11: Application Example: Photo OCR
11.1. Photo OCR