Stanford University 2014 (Wu Enda) Machine Learning Course Chinese Notes
course address:https://www.coursera.org/course/ml
Machine Learning (Machine Learning) is the study of how computers simulate or implement human learning behaviors to acquire new knowledge or skills, and reorganize existing knowledge structures to continuously improve their own performance. It is the core of artificial intelligence and the fundamental way to make computers intelligent. Its application pervades all fields of artificial intelligence. It mainly uses induction and synthesis instead of deduction. Over the past decade, machine learning has helped us drive self-driving cars, perform efficient speech recognition, perform efficient web searches, and dramatically improve our understanding of the human genome. Machine learning is so prevalent today that you probably use it dozens of times a day without knowing it. Many researchers also believe that this is the best way to obtain artificial intelligence. In this class, you'll learn the most effective machine learning techniques and gain practice putting them to work for yourself. What's more, you'll learn not only the theoretical foundations, but also the practical techniques that require fast and powerful application of techniques to solve problems. Finally, you'll learn about some of Silicon Valley's best practice innovations utilizing machine learning and artificial intelligence.
This course provides a broad introduction to machine learning, data mining, and statistical pattern recognition. Topics include:
(一)Supervised learning (parametric/nonparametric algorithms, support vector machines, kernel functions, neural networks)。
(二)Unsupervised learning (clustering, dimensionality reduction, recommendation system, deep learning recommendation)。
(三)Best Practices in Machine Learning (Bias/Variance Theory; Innovation Processes in Machine Learning and AI). The course will also use extensive case studies and you will also learn how to use learning algorithms to build intelligent robots (perception, control), understanding of text (Web search, anti-spam), computer vision, medical informatics, audio , data mining, and other fields.
This course requires a total of 18 lessons in 10 weeks. Compared with the previous machine learning videos, this video is clearer, and each lesson has ppt courseware, which is recommended for learning.
I started to translate the subtitles of this course in the second half of 2014, and wrote the Chinese notes of the course. The notes have been downloaded tens of thousands of times, which should have helped many people, and many people have been helping me. Now I share the word and markdown manuscripts of the notes with you.
I will put markdown notes and course Chinese and English subtitles on github, I hope everyone can continue to improve. In order to facilitate the online display of mathematical formulas, the html file is viewed online, the formula has been converted into a picture, and the source code of the formula is in the markdown file。
Finally, I want to say to my friends: Gifts of roses, hand a fragrance! On the road of artificial intelligence, you are not alone!
Huang Haiguang
2018-3-26 My Zhihu
reference:https://www.coursera.org/course/ml Machine Learning Open Course
"Statistical Learning Methods" Li Hang
"Machine Learning Class" Zou Bo
备注:吴恩达老师的深度学习课(deepLearning.ai)的笔记地址:https://github.com/fengdu78/deeplearning_ai_books
Folder description:
docx: word version of notes
markdown: markdown version of notes
html: the html version of the note
images: pictures of notes
ppt: The original courseware of the course
srt: The Chinese and English subtitles of the course (mp4 files need to be downloaded from Baidu Cloud, you can use Notepad or subtitle editing software to edit subtitles and improve them together, Baidu Cloud link: https://pan. baidu.com/s/1h8QjqBlOm0Exh7orm9teMQ Password: d3we, unzip after downloading)
code: python code of the course (some of them are written by foreign experts)
Machine learning video download link: https://pan.baidu.com/s/1raoOPOg Password: 48m8, including video and subtitles, unzip after downloading, it is recommended to use potplayer to play, this video is consistent with mp4 .
[Notes online reading] (http://www.ai-start.com/ml2014)
Note pdf version download: see github root directory.
Machine learning qq group: 865189078 (we have 8 groups, if you add one, you don’t need to add it)
- Introduction (Introduction)
1.1 welcome
1.2 What is machine learning?
1.3 Supervised Learning
1.4 Unsupervised Learning
- Univariate linear regression (Linear Regression with One Variable)
2.1 Model Representation
2.2 Cost function
2.3 Intuitive understanding of cost function I
2.4 Intuitive Understanding of Cost Function II
2.5 Gradient Descent
2.6 Intuitive understanding of gradient descent
2.7 Linear Regression with Gradient Descent
2.8 What's Next
- Linear Algebra Review (Linear Algebra Review)
3.1 Matrices and vectors
3.2 Addition and scalar multiplication
3.3 Matrix-vector multiplication
3.4 Matrix multiplication
3.5 Properties of matrix multiplication
3.6 Reverse, Transpose
- Multivariate linear regression (Linear Regression with Multiple Variables)
4.1 Multidimensional features
4.2 Multivariate Gradient Descent
4.3 Gradient Descent Method Practice 1 - Feature Scaling
4.4 Gradient descent method practice 2-learning rate
4.5 Eigen and polynomial regression
4.6 Normal equations
4.7 Normal equations and irreversibility (optional)
- Octave Tutorial (Octave Tutorial)
5.1 Basic operation
5.2 Mobile data
5.3 Calculation data
5.4 Drawing data
5.5 Control statements: for, while, if statements
5.6 Vectorization 88
5.7 Working and submitting programming exercises
- Logistic regression (Logistic Regression)
6.1 Classification problems
6.2 Hypothesis representation
6.3 Decision boundary
6.4 Cost Function
6.5 Simplified cost functions and gradient descent
6.6 Advanced optimization
6.7 Multi-class classification: one-vs-many
- Regularization (Regularization)
7.1 The problem of overfitting
7.2 Cost Function
7.3 Regularized Linear Regression
7.4 Regularized Logistic Regression Models
Eighth, neural network: representation (Neural Networks: Representation)
8.1 Nonlinear assumptions
8.2 Neurons and the Brain
8.3 Model Representation 1
8.4 Model Representation 2
8.5 Samples and intuitions1
8.6 Samples and Intuitive Understanding II
8.7 Multiclass classification
Nine, neural network learning (Neural Networks: Learning)
9.1 Cost Function
9.2 Backpropagation Algorithm
9.3 Intuitive Understanding of the Backpropagation Algorithm
9.4 Implementation Note: Expand Parameters
9.5 Gradient testing
9.6 Random initialization
9.7 Putting it all together
9.8 Autonomous Driving
- Advice for Applying Machine Learning (Advice for Applying Machine Learning)
10.1 Deciding what to do next
10.2 Evaluating a hypothesis
10.3 Model selection and cross-validation sets
10.4 Diagnostic Bias and Variance
10.5 Regularization and bias/variance
10.6 Learning Curve
10.7 Deciding what to do next
- Design of Machine Learning System (Machine Learning System Design)
11.1 What to do first
11.2 Error Analysis
11.3 Error Metrics for Class Skewness
11.4 The Trade-Off Between Precision and Recall
11.5 Data for Machine Learning
- Support Vector Machines (Support Vector Machines)
12.1 Optimization objectives
12.2 Intuitive Understanding of Large Boundaries
12.3 Large-boundary classification behind the mathematics (optional)
12.4 Kernel function 1
12.5 Kernel functions 2
12.6 Using Support Vector Machines
Thirteen, clustering (Clustering)
13.1 Unsupervised Learning: An Introduction
13.2 K-Means Algorithm
13.3 Optimization Objectives
13.4 Random initialization
13.5 Choosing the number of clusters
- Dimensionality Reduction (Dimensionality Reduction)
14.1 Motivation One: Data Compression
14.2 Motivation Two: Data Visualization
14.3 Principal Component Analysis Problems
14.4 Principal Component Analysis Algorithm
14.5 Choosing the number of principal components
14.6 Compressed Representation for Reconstruction
14.7 Suggestions for the application of principal component analysis
- Anomaly Detection (Anomaly Detection)
15.1 Motivation for the question
15.2 Gaussian distribution
15.3 Algorithms
15.4 Developing and evaluating an anomaly detection system
15.5 Anomaly Detection vs. Supervised Learning
15.6 Selecting features
15.7 Multivariate Gaussian distribution (optional)
15.8 Anomaly Detection Using Multivariate Gaussian Distributions (Optional)
- Recommender Systems (Recommender Systems)
16.1 Formalizing the problem
16.2 Content-Based Recommender Systems
16.3 Collaborative filtering
16.4 Collaborative filtering algorithm
16.5 Vectorization: Low-rank matrix factorization
16.6 Implementation Details: Mean Normalization
Seventeen, large-scale machine learning (Large Scale Machine Learning)
17.1 Learning from Large Datasets
17.2 Stochastic Gradient Descent
17.3 Mini-batch gradient descent
17.4 Stochastic Gradient Descent Convergence
17.5 Online Learning
17.6 Map reduction and data parallelism
- Application Example: Image Text Recognition (Application Example: Photo OCR)
20.1 Problem description and flowchart
18.2 Sliding windows
18.3 Acquiring large amounts of data and artificial data
18.4 Upper limit analysis: which part of the pipeline to do next
- Summary (Conclusion)
19.1 Summary and Acknowledgments