Six Classifications of Artificial Intelligence

Deep learning

Deep learning is a new field of machine learning, which is based on the existing data. It is to build and simulate the neural network of human brain for analysis and learning.

It mimics the mechanism of the human brain to interpret data, such as images, sounds and texts. Deep learning is a kind of unsupervised learning.


natural language processing

Natural Language Processing (NLP) is a technology that uses natural language to communicate with computers. A branch of artificial intelligence that studies the use of computers to simulate human language communication.

To enable computers to understand and use the natural languages of human society, such as Chinese and English, so as to realize the natural language communication between human and computer, so as to replace part of human mental work.

It includes inquiries, answers to questions, excerpts, compilations and processing of all relevant natural language information. For example, the core technology of telephone robots in life

One is natural language processing.


computer vision

Computer vision refers to the use of cameras and computers instead of human eyes for target recognition, tracking and measurement, and further graphic processing to make computer processing more appropriate.

An image that is observed by the human eye or transmitted to the instrument for detection.

Computer vision is to use various imaging systems instead of visual organs as input sensitive means, and computers instead of the brain to complete processing and interpretation. The Final Research of Computer Vision

The goal is to enable computers to observe and understand the world through vision, like human beings, and have the ability to adapt to the environment independently. There are many examples of computer vision applications, including for control.

System process, navigation, automatic detection and so on.


intelligent robot

Nowadays, there are many intelligent robots around us. They have all kinds of internal and external information sensors, such as vision, hearing, touch, etc.

Smell. In addition to having receptors, it also has effective receptors as a means of acting on the surrounding environment. These robots are inseparable from the technical support of artificial intelligence.

Scientists believe that the research and development direction of intelligent robots is to equip robots with "brain chips" so as to make them more intelligent, in cognitive learning, automatic organization, and fuzzy information.

A great step forward will be made in the comprehensive treatment of information.


Automatic Programming

Automatic programming refers to the automatic generation of programs that meet the requirements according to the original description of a given problem. It is a research subject combining software engineering and artificial intelligence. Automatic program

The design mainly includes two aspects: program synthesis and program verification. The former implements automatic programming, that is, the user only needs to tell the machine "what to do" without telling "how to do", the latter step.

The work is done automatically by the machine; the latter is the automatic verification of the program, which automatically completes the correctness check. Its purpose is to improve software productivity and product quality.

The task of automatic programming is to design a program system, accept a very high-level description of the program's requirements to achieve a certain goal as its input, and then automatically generate it.

This is a specific procedure to achieve this goal. One of the major contributions of this research is to use the concept of program debugging as a problem solving strategy.


data mining

Data mining generally refers to the process of searching hidden information from a large number of data through algorithms. It is usually related to computer science, and through the Statistical and Online Analytical Office.

Many methods such as science, information retrieval, machine learning, expert system (relying on past experience rules) and pattern recognition are used to achieve the above goals. Its analytical methods include:

Class, estimation, prediction, correlation grouping or association rules, clustering and complex data type mining.


Reference: https://baijiahao.baidu.com/s? Id=1607385160045586500 & wfr=spider&for=pc