Top in the whole network, it is no exaggeration to say that this Stanford machine learning tutorial in Chinese notes can help you learn from the beginning to the mastery of machine learning

Artificial intelligence

Artificial intelligence , It is undoubtedly the most popular concept now , from AlphaGo After defeating lishishi , The world has set off a wave of artificial intelligence . We are in every corner of life , Can feel that a new singularity era is coming

Artificial intelligence inflatable insole

Artificial intelligence toilet

( You can change the music with your shit mood )

OMG！ Only we can't think of , There is nothing magical that artificial intelligence cannot do ！ From the insole to the toilet, they are all equipped with artificial intelligence , In the future, if artificial intelligence attacks humans , Are you going to be barefoot 、 The toilet can't be used ！

However, it is worth pointing out that , Several concepts are now rampant , Including artificial intelligence 、 machine learning 、 Deep learning and neural networks , In fact, it is not completely equivalent . Strictly speaking , They are a smaller and smaller relationship ,

So here comes the question , For non computer professionals , When someone talks to you about artificial intelligence , How to judge whether what he is doing is machine learning (Machine Learning) Or artificial intelligence (Artificial Intelligence) Well ？

Here we can introduce a simple and practical method , That is to ask him to send a screenshot of his usual work , If it is similar to the following figure , So that is machine learning （ Probability is also deep learning ）

And if it is similar to the figure below

So as the figure shows , He is engaged in Artificial intelligence .

As a brick moving worker who is nominally engaged in the part of artificial intelligence that belongs to machine learning , After the first-line machine learning practice and Research ,LR Deeply touched by this subject . therefore LR From the bottom of my heart, I hereby propose ： Everyone should learn machine learning , This subject is full of life philosophy and wisdom beyond narrow computer science , It is a compulsory course for every contemporary youth .

Here I recommend a Chinese note of Stanford machine learning course , The Ultimate Classic , It can be called the first choice of zero foundation Xiaobai entry . The corresponding video tutorial has been uploaded to https://www.coursera.org/course/ml

This book provides an extensive introduction to machine learning 、 data mining 、 Chapter on statistical pattern recognition . Topics include ：
（ One ） Supervised learning （ Parameters / Nonparametric algorithm , Support vector machine , Kernel function , neural network ）.
（ Two ） Unsupervised learning
（ clustering , Dimension reduction , Recommendation system , In depth study is recommended ）.
（ 3、 ... and ） Best practices in machine learning （ deviation / Variance theory ; In the innovation process of machine learning and artificial intelligence ）. This course will also use a large number of case studies , You will also learn how to use learning algorithms to build intelligent robots （ perception , control ）, The understanding of the text （Web Search for , anti-spam ）, meter
Computer vision , Medical information , Audio , data mining , And other areas .

Friends, if you need a full set of 《 Stanford machine learning tutorial Chinese Notes 》PDF, Scan the QR code below for free （ In case of code scanning problem , Comment area message collection ）~

The first week

One 、 introduction (Introduction)

1.1 welcome

1.2 What is machine learning ？

1.3 Supervised learning

1.4 Unsupervised learning

Two 、 Univariate linear regression **(Linear Regression with One Variable**)

2.1 Model to represent

2.2 Cost function

2.3 An intuitive understanding of the cost function I

2.4 An intuitive understanding of the cost function II

2.5 gradient descent

2.6 An intuitive understanding of gradient descent

2.7 Linear regression of gradient descent

2.8 What's next

3、 ... and 、 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 The properties of matrix multiplication

3.6 The inverse 、 Transposition

In the second week of

Four 、 Multivariate linear regression (Linear Regression with Multiple Variables)

4.1 Multidimensional characteristics

4.2 Multivariable gradient descent

4.3 Gradient descent method practice 1- Feature scaling

4.4 Gradient descent method practice 2- Learning rate

4.5 Characteristic and polynomial regression

4.6 Normal equation

4.7 Normal equations and irreversibility （ Elective ）

5、 ... and 、Octave course (Octave Tutorial)

5.1 Basic operation

5.2 mobile data

5.3 Calculate the data

5.4 The drawing data

5.5 Control statement ：for,while,if sentence

5.6 To quantify 88

5.7 Work and submit programming exercises

Friends, if you need a full set of 《 Stanford machine learning tutorial Chinese Notes 》PDF, Scan the QR code below for free （ In case of code scanning problem , Comment area message collection ）~

The third week

6、 ... and 、 Logical regression (Logistic Regression)

6.1 Classification problem

6.2 The hypothesis is that

6.3 Determine the boundary

6.4 Cost function

6.5 Simplified cost function and gradient descent

6.6 Advanced optimization

6.7 Multi category classification ： One to many

7、 ... and 、 Regularization (Regularization)

7.1 The problem of over fitting

7.2 Cost function

7.3 Regularize linear regression

7.4 Regularized logistic regression model

The fourth week

The eighth 、 neural network ： describe (Neural Networks: Representation)

8.1 Nonlinear hypothesis

8.2 Neurons and the brain

8.3 Model to represent 1

8.4 Model to represent 2

8.5 Sample and intuitive understanding 1

8.6 Sample and intuitive understanding II

8.7 Multiple categories

Week 5

Nine 、 Learning neural networks (Neural Networks: Learning)

9.1 Cost function

9.2 Back propagation algorithm

9.3 Intuitive understanding of back propagation algorithm

9.4 Implementation note ： Expand parameters

9.5 Gradient inspection

9.6 Random initialization

9.7 combined

9.8 Autonomous driving

Week six

Ten 、 Suggestions for applied machine learning (Advice for Applying Machine Learning)

10.1 Decide what to do next

10.2 Evaluate a hypothesis

10.3 Model selection and cross validation set

10.4 Diagnostic bias and variance

10.5 Regularization and deviation / variance

10.6 The learning curve

10.7 Decide what to do next

11、 ... and 、 The design of machine learning system (Machine Learning System Design)

11.1 What to do first

11.2 error analysis

11.3 The error measure of class skew

11.4 The tradeoff between precision and recall

11.5 Machine learning data

Friends, if you need a full set of 《 Stanford machine learning tutorial Chinese Notes 》PDF, Scan the QR code below for free （ In case of code scanning problem , Comment area message collection ）~

The first 7 Zhou

Twelve 、 Support vector machine (Support Vector Machines)

12.1 Optimization objectives

12.2 The intuitive understanding of the big boundary

12.3 The mathematics behind big boundary classification （ Elective ）

12.4 Kernel function 1

12.5 Kernel function 2

12.6 Using support vector machines

The first 8 Zhou

13、 ... and 、 clustering (Clustering)

13.1 Unsupervised learning ： brief introduction

13.2 K- Mean algorithm

13.3 Optimization objectives

13.4 Random initialization

13.5 Select the number of clusters

fourteen 、 Dimension reduction (Dimensionality Reduction)

14.1 Motive one ： data compression

14.2 Motivation two ： Data visualization

14.3 Principal component analysis problem

14.4 Principal component analysis algorithm

14.5 Choose the number of principal components

14.6 Reconstructed compressed representation

14.7 Suggestions on the application of principal component analysis

Week 9

15、 ... and 、 Anomaly detection (Anomaly Detection)

15.1 The motivation of the problem

15.2 Gaussian distribution

15.3 Algorithm

15.4 Develop and evaluate an anomaly detection system

15.5 Comparison between anomaly detection and supervised learning

15.6 Select features

15.7 Multivariate Gaussian distribution （ Elective ）

15.8 Using multivariate Gaussian distribution for anomaly detection （ Elective ）

sixteen 、 Recommendation system (Recommender Systems)

16.1 Problem formalization

16.2 Content based recommendation system

16.3 Collaborative filtering

16.4 Collaborative filtering algorithm

16.5 To quantify ： Low rank matrix decomposition

16.6 Details of implementation work ： Mean normalization

Week 10

seventeen 、 Large scale machine learning (Large Scale Machine Learning)

17.1 Learning from large data sets

17.2 Random gradient descent method

17.3 Small batch gradient descent

17.4 Stochastic gradient descent convergence

17.5 Online learning

17.6 Mapping simplification and data parallelism

eighteen 、 Application example ： Picture text recognition (Application Example: Photo OCR)

18.1 Problem description and flow chart

18.2 The sliding window

18.3 Get a lot of data and human data

18.4 Limit analysis ： Which part of the pipeline will be done next

nineteen 、 summary (Conclusion)

19.1 Summary and thanks

Friends, if you need a full set of 《 Stanford machine learning tutorial Chinese Notes 》PDF, give the thumbs-up + Comment on Stanford machine learning tutorial Chinese Notes , I will reply one by one ！