When it comes to the definition of artificial intelligence (AI), the key words that come to mind may be "future" and "science fiction". Although these factors seem far away from us, they are part of our daily life. The popularity of voice assistants, the success of unmanned driving, artificial intelligence, machine learning and deep learning have penetrated into every scene of our lives. For example, JD.COM will use an algorithm to recommend the goods you need according to your browsing behavior and the similarity of users; Another example is a beauty camera, which will extract your beauty effect through an algorithm based on the analysis of your facial features. There is also the well-known Google DeepMind. When AlphaGo defeated Li Shishi, a Korean professional Go player, the media mentioned artificial intelligence AI, machine learning, deep learning and other terms when describing the man-machine war. Yes, these three technologies have made great contributions to AlphaGo's victory, but they are not the same thing.

Artificial intelligence and machine learning appear at the same time, and machine learning and deep learning are used alternately ... which makes most readers confused. What is the difference between these concepts? We can distinguish them by the picture below.

Figure 1: the relationship between artificial intelligence, machine learning and deep learning.

Artificial intelligence includes machine learning and deep learning, and machine learning includes deep learning. Artificial intelligence is the parent class of machine learning, and machine learning is the parent class of deep learning.

Artificial intelligence (AI) is a branch of computer science, which tries to understand the nature of intelligence and produce a new intelligent machine that responds in a way similar to human intelligence. It is not human intelligence, but it can think like human intelligence, or it may surpass human intelligence.

Practical applications of artificial intelligence: machine vision, fingerprint recognition, face recognition, retina recognition, iris recognition, palmprint recognition, expert system, automatic planning, intelligent search, theorem proving, games, automatic programming, intelligent control, robotics, language and image understanding, genetic programming, etc. At present, artificial intelligence is also divided into bottom-up AI and top-down AI.

Machine learning (ML) is the core of artificial intelligence and belongs to a branch of artificial intelligence. Machine learning refers to an algorithm that automatically analyzes and obtains rules from data and uses the rules to predict unknown data, so the core of machine learning is data, algorithm (model) and computing power (computer computing power).

Application fields of machine learning: data mining, data classification, computer vision, natural language processing (NLP), biometrics, search engines, medical diagnosis, credit card fraud detection, securities market analysis, DNA sequencing, voice and handwriting recognition, strategic games and robot applications.

Deep learning (DL) is a new field of machine learning research. Its motivation lies in establishing and simulating the neural network of human brain for analysis and learning, and imitating the mechanism of human brain to interpret data.

Data Mining (DM), as its name implies, refers to the use of machine learning technology to "mine" hidden information from massive data, which is mainly applied to images, sounds and texts. In the business environment, enterprises hope that the data stored in the database can "speak" and support decision-making. So data mining is more application-oriented.

Figure 2: The relationship between data mining and machine learning

Machine learning is an important method of data mining, but machine learning is another discipline, not subordinate to data mining, and the two complement each other. Data mining is the intersection of machine learning and database, which mainly uses the technology provided by machine learning to analyze massive data and uses the technology provided by database community to manage massive data.

Whether it is artificial intelligence, machine learning, deep learning or data mining, they all play their respective advantages in solving the same goal, providing convenience for social production and human life, helping us explore the past, show the present situation and predict the future.