Machine Learning Concept Principles and Common Algorithms

concept:

Machine Learning (ML) is a multi-field interdisciplinary subject involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. It specializes in how computers simulate or realize human learning behaviors to acquire new knowledge or skills, and to reorganize existing knowledge structures to continuously improve their performance.

It is the core of artificial intelligence and the fundamental way to make computers intelligent. It is applied in all fields of artificial intelligence. It mainly uses induction and synthesis instead of deduction.

Teaching Session: Introduction to Machine Learning Concepts

(The course mainly explains the concepts, principles and application scenarios of machine learning, as well as commonly used algorithms for machine learning, such as supervised learning, unsupervised learning, linear regression, etc.)

Machine learning is a relatively young branch of artificial intelligence research, and its development process can be roughly divided into four periods.

The first stage was from the mid-1950s to the mid-1960s, which belonged to the warm period.

The second phase was from the mid-1960s to the mid-1970s, known as the cool-off period of machine learning.

The third phase, from the mid-1970s to the mid-1980s, is called the Renaissance.

The latest phase of machine learning started in 1986.

The important manifestations of machine learning entering a new stage are in the following aspects:

(1) Machine learning has become a new fringe subject and has formed a course in colleges and universities. It integrates the application of psychology, biology and neurophysiology as well as mathematics, automation and computer science to form the theoretical foundation of machine learning.
(2) Combined with various learning methods, the research of various forms of integrated learning systems is emerging. In particular, the coupling of connection learning and symbolic learning can better solve the problem of acquisition and refinement of knowledge and skills in continuous signal processing.
(3) A unified view of various fundamental issues of machine learning and artificial intelligence is taking shape. For example, the view that learning is combined with problem solving and knowledge expression facilitates learning has resulted in the block learning of the general intelligence system SOAR. The case-based method combining analogical learning and problem solving has become an important direction of empirical learning.
(4) The scope of application of various learning methods has been expanding, and some of them have become commodities. Knowledge acquisition tools for inductive learning have been widely used in diagnostic classification expert systems. Connection learning is dominant in audiovisual recognition. Analytical learning has been used to design comprehensive expert systems. Genetic algorithm and reinforcement learning have good application prospects in engineering control. The neural network connection learning coupled with the symbolic system will play a role in the intelligent management of enterprises and the motion planning of intelligent robots.

(5) Academic activities related to machine learning are unprecedentedly active. In addition to the annual machine learning seminar, there are also computer learning theory conferences and genetic algorithm conferences .

syllabus

Course hours:

Chapter 1: Machine Learning Concepts, Principles, and Application Scenarios

Lesson 1: Basic Concepts of Machine Learning 16:06

Session 2: The Domain of Machine Learning 11:50

Lesson 3: Why Machines Can Learn 08:17

Chapter 2: Common Algorithms for Machine Learning

Session 4: Supervised Learning - Linear Regression 14:22

Lesson 5: Nonlinear regression, overfitting, model selection 06:33

Lesson 6: Supervised Learning Classification 05:26

Lesson 7: Unsupervised Learning 12:06

Chapter 3: Summary and Exercises