An article clarifies the differences and links between AI, machine learning and in-depth learning.

Reproduced from:

Http://blog.sciencenet.cn/blog-2888249-1082369.html

The tide of artificial intelligence is sweeping the world, and many words are lingering in our ears all the time: Artificial Intelligence, Machine Learning and Deep Learning. Many people always seem to understand the meaning of these high-frequency words and the relationship behind them.

In order to help you better understand AI, this article explains the meanings of these words in the simplest language and clarifies the relationship between them, hoping to help the newcomers.

An article clarifies the differences and links between AI, machine learning and in-depth learning.

Fig. 1 Application of Artificial Intelligence

Artificial Intelligence: From Concept to Prosperity

In 1956, several computer scientists gathered in Dartmouth to propose the concept of "artificial intelligence", dreaming of using the computers that had just emerged at that time to construct complex machines with the same essential characteristics as human intelligence. Since then, artificial intelligence has been lingering in people's minds, and slowly incubated in scientific research laboratories. For decades afterwards, AI has been reversing its polarity, or being called the prophecy of the dazzling future of human civilization, or being thrown into the garbage dump as the fantasy of a technological madman. Until 2012, both voices still existed.

After 2012, thanks to the increase of data volume, the improvement of computing power and the emergence of new machine learning algorithms (in-depth learning), artificial intelligence began to explode. According to the "Global AI Talents Report" released recently by Link UK, as of the first quarter of 2017, the number of global AI (Artificial Intelligence) technology talents based on Link UK platform exceeded 1.9 million, and the gap of domestic AI talents reached more than 5 million.

The field of AI research is also expanding. Fig. 2 shows the branches of AI research, including expert systems, machine learning, evolutionary computing, fuzzy logic, computer vision, natural language processing, recommendation systems, etc.

An article clarifies the differences and links between AI, machine learning and in-depth learning.

Fig. 2 Artificial Intelligence Research Branch

But the current research work is concentrated on the weak AI part, and it is hopeful to make a major breakthrough in the near future. The AI in movies is mostly depicting the strong AI, which is difficult to really realize in the current real world (usually divided into the weak AI and the strong AI. The former enables the machine to have the ability of observation and perception. To achieve a certain degree of understanding and reasoning, and strong artificial intelligence allows the machine to acquire adaptive ability to solve some problems that have not been encountered before.

Weak AI is expected to make breakthroughs. How can it be realized? Where does "intelligence" come from? This is mainly due to a method of realizing artificial intelligence - machine learning.

Learn the relevant knowledge of artificial intelligence technology, you can learn about online education platform - Deep Blue College. Deep Blue College is an online education platform devoted to the frontier science and technology such as artificial intelligence.

Machine Learning: A Method to Realize Artificial Intelligence

The most basic method of machine learning is to use algorithms to parse data, learn from them, and then make decisions and predictions about real world events. Unlike traditional hard-coded software programs for specific tasks, machine learning uses a large amount of data to "train" and learns how to accomplish tasks from data through various algorithms.

For example, when we browse the online shopping mall, we often have the information of product recommendation. It's the mall that identifies which products you're really interested in and willing to buy based on your past shopping records and lengthy collection lists. Such a decision-making model can help the mall provide suggestions to customers and encourage product consumption.

Machine learning comes directly from the early field of artificial intelligence. Traditional algorithms include decision tree, clustering, Bayesian classification, support vector machine, EM, Adaboost and so on. In terms of learning methods, machine learning algorithms can be divided into supervised learning (such as classification problems), unsupervised learning (such as clustering problems), semi-supervised learning, ensemble learning, in-depth learning and reinforcement learning.

Traditional machine learning algorithms in fingerprint recognition, Haar-based face detection, HoG-based object detection and other fields basically meet the requirements of commercialization or the level of commercialization of specific scenarios, but each step is extremely difficult until the emergence of deep learning algorithms.

Deep Learning: A Technology to Realize Machine Learning

Deep learning is not an independent learning method, and it also uses supervised and unsupervised learning methods to train deep neural networks. However, due to the rapid development of this field in recent years, some unique learning methods have been proposed one after another (such as residual network), so more and more people regard it as a learning method alone.

Initial deep learning is a learning process that uses deep neural network to solve feature expression. Deep neural network is not a new concept in itself. It can be roughly understood as a neural network structure with multiple hidden layers. In order to improve the training effect of deep-seated neural network, people have made corresponding adjustments to the connection method and activation function of neurons. In fact, there were many ideas in the early years, but because of the insufficient training data and backward computing ability, the ultimate effect was not satisfactory.

Please read the Chinese version for details.