Machine learning 01: Introduction

Definition of machine learning

Machine learning is one of the core research fields of artificial intelligence , Its research motivation is to make the computer system have human learning ability in order to realize artificial intelligence .
At present, the widely used definition of machine learning is “ Use experience to improve the performance of computer system itself ”. because “ Experience ” In the computer system, it mainly exists in the form of data , Therefore, machine learning needs to use machine learning technology to analyze data , This makes it gradually become one of the innovative sources of intelligent data analysis technology , And for this reason, it has attracted more and more attention .

Machine learning and data mining

When people are talking about machine learning , I often think of another intelligent data analysis technology ： data mining .
Data mining is ：“ Identify effective in huge amounts of data 、 Novel 、 Potentially useful 、 The non trivial process of ultimately comprehensible patterns ”. seeing the name of a thing one thinks of its function , Data mining is trying to find useful knowledge from massive data .
The relationship between machine learning and data mining can be understood through the following two data mining textbooks ：

• so , Data mining textbooks and courses mainly explain various data mining tasks . such as ： classification 、 Return to 、 clustering 、 Correlation analysis 、 Abnormal analysis 、 Evolution analysis and so on .
• Data mining can be regarded as the intersection of machine learning and database , It mainly uses the technology provided by the machine learning community to analyze massive data , Use the technology provided by the database industry to manage massive data .
• There are differences and connections between the two , As a whole , Machine learning theory , Data mining tends to be applied .

Machine learning technology

• The first 1 Chapter , Explain the definition of machine learning 、 And data mining 、 The teaching idea and content arrangement of this course 、 Teaching materials and reference books
• The first 2 Chapter , Explain the method of model evaluation 、 Indicators and comparative tests .
• The first 3-9 Chapter , Explain the basic technology of machine learning ： Start with linear regression , Explain linear learning ; With K Mean clustering closure , Explain unsupervised learning ; Support vector machine learning 、 Neural network learning 、 Decision tree learning 、 Bayesian learning 、 And the nearest neighbor .
• The first 10-13 Chapter , Explain the advanced technology of machine learning ： Specifically, it includes integrated learning 、 Cost sensitive learning 、 Evolutionary learning 、 And reinforcement learning .

Definition of classification

• Classification is to build a classification model , The classifier , Then the process of mapping data objects to a given category through a classifier . The classification process can be divided into two steps ：
• The first step is to use the training data set with known class markers to learn the classification model . This step is called the training stage of the classifier .
• The second step is to test and evaluate the performance of the learned model （ This step is called the test phase of the classifier ）, If the performance of the model is acceptable , It can be used to classify objects marked by unknown classes .
• The third step is to apply the classification model to classify the objects marked by unknown classes . This step is called the working stage of the classifier .
• Classification is a three-step process ： Training → test → Work .

Teaching materials and special instructions

The teaching material

In particular

This blog is the author's study notes , The main content comes from machine learning _ China university of geosciences MOOC, By the author in his spare time 、 Record , Just for learning 、 Review the use of , Not for commercial use , Shall not be reproduced , The following are the teachers of this course .