What are the classifications of artificial intelligence?

Six categories of artificial intelligence:

1, deep learning:

Deep learning is a learning operation based on existing data and a new field of machine learning research. The machine is to establish and simulate the neural network of human brain for analysis and learning, and imitate the mechanism of human brain to interpret data, examples, sounds and texts. Deep learning is an unsupervised learning.

2, natural language processing:

Natural language processing is a technology that uses natural language to communicate with computers. A branch of artificial intelligence, which studies the process of using electronic computers to simulate human language communication, so that computers can understand and use natural languages of human society, such as Chinese and English, and realize natural language communication between human and computer, instead of being a part of human mental work, including querying materials, answering questions, extracting documents, compiling materials and processing all information about natural languages. For example, one of the core technologies of telephone robots in life is natural language processing.

3, computer vision:

Computer vision refers to the use of cameras and computers to identify, track and measure targets instead of human eyes, and further graphic processing, so that computers can be processed into images more suitable for human eyes to observe or sent to instruments for detection; Computer vision uses various imaging systems instead of visual organs as input sensitive means, and computers instead of brains to complete processing and interpretation. The ultimate research goal of computer vision is to enable computers to observe and understand the world through vision like people, and have the ability to adapt to the environment independently. There are many examples of computer vision applications, including control process, navigation, automatic detection and so on.

4, intelligent robot:

Nowadays, there are many intelligent robots around us. They have various internal information sensors and external information sensors, such as vision, hearing, touch and smell. In addition to receptors, it also has effectors as a means to act 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" to make them smarter, which will make robots take a big step forward in cognitive learning, automatic organization and comprehensive processing of fuzzy information.

5, automatic programming:

Automatic programming refers to automatically generating programs that meet the requirements according to the original description of a given problem. It is a research subject combining software engineering with artificial intelligence. Automatic programming mainly includes program synthesis and program verification. The former realizes automatic programming, that is, the user only needs to tell the machine "what to do" instead of "how to do it", and the next step is automatically completed 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 software product quality; The task of automatic programming is to design a program system, accept the very advanced description that the designed program needs to achieve a certain goal as its input, and then automatically generate a specific program that can accomplish this goal. One of the great contributions of this research is to take the concept of program debugging as a problem-solving strategy.

6, data mining:

Data mining generally refers to the process of finding hidden information from a large number of data through algorithms. It is usually related to computer science, and achieves the above goals through statistics, online analytical processing, information retrieval, machine learning, expert system (relying on past empirical rules) and pattern recognition. Its analysis methods include: classification, estimation, prediction, related grouping or association rules, clustering and complex data type mining.