What is the difference between artificial intelligence, machine learning and deep learning?
Provide a learning route and book list, thank you!
Educate
Deep Blue College, the public account "Deep Blue Education Service Account"
The wave of artificial intelligence is sweeping the world, and many words linger 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 everyone better understand artificial intelligence, this article uses the simplest language to explain the meaning of these words and clarify the relationship between them. I hope it will be helpful to colleagues who are just getting started.
Figure 1 Application of artificial intelligence
Artificial Intelligence: From Concept Proposal to Prosperity
In 1956, several computer scientists gathered at the Dartmouth Conference and proposed the concept of "artificial intelligence", dreaming of using computers that had just appeared 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. In the following decades, artificial intelligence has been reversing the poles, or it is called the prediction of the dazzling future of human civilization, or it is thrown into the garbage dump as the fantasies of technological lunatics. Until 2012, these two voices still existed at the same time.
After 2012, thanks to the increase in data volume, the increase in computing power and the emergence of new machine learning algorithms (deep learning), artificial intelligence began to explode. According to the "Global AI Talent Report" recently released by LinkedIn, as of the first quarter of 2017, the number of global AI (artificial intelligence) technical talents based on the LinkedIn platform exceeded 1.9 million, and the domestic artificial intelligence talent gap reached more than 5 million. .
The research field of artificial intelligence is also expanding. Figure 2 shows the various branches of artificial intelligence research, including expert systems, machine learning, evolutionary computing, fuzzy logic, computer vision, natural language processing, recommendation systems, etc.
Figure 2 Artificial Intelligence Research Branch
However, the current scientific research work is focused on weak artificial intelligence, and it is hoped that major breakthroughs will be made in the near future. Most of the artificial intelligence in the movie depicts strong artificial intelligence, and this part is difficult to truly realize in the current real world. (Artificial intelligence is usually divided into weak artificial intelligence and strong artificial intelligence. The former allows the machine to have the ability to observe and perceive, and it can achieve a certain degree of understanding and reasoning, while the strong artificial intelligence allows the machine to acquire adaptive capabilities and solve some problems that have not been Problems encountered).
Weak artificial intelligence has hopes of making breakthroughs. How did it achieve it, and where does "intelligence" come from? This is mainly due to a method of achieving artificial intelligence-machine learning.
Machine learning: a way to achieve artificial intelligence
The most basic method of machine learning is to use algorithms to parse data, learn from it, and then make decisions and predictions about events in the real world. Unlike traditional software programs that are hard-coded to solve specific tasks, machine learning uses large amounts of data to "train" and learn how to complete tasks from the data through various algorithms.
To give a simple example, when we browse online shopping malls, product recommendations often appear. This is based on your past shopping records and a lengthy collection list, the mall identifies which of these are the products you are really interested in and are willing to buy. Such a decision-making model can help the mall provide customers with suggestions and encourage product consumption.
Machine learning comes directly from the early artificial intelligence field. Traditional algorithms include decision trees, clustering, Bayesian classification, support vector machines, 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, deep learning, and reinforcement learning.
The application of traditional machine learning algorithms in the fields of fingerprint recognition, Haar-based face detection, and HoG feature-based object detection has basically reached the requirements of commercialization or the level of commercialization of specific scenarios, but every step forward is extremely difficult until The emergence of deep learning algorithms.
Deep learning: a technology for realizing machine learning
Deep learning is not originally an independent learning method, it will also use 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 (such as residual networks), so more and more people regard it as a learning method alone.
The original deep learning is a learning process that uses deep neural networks to solve feature expression. Deep neural network itself is not a new concept, but can be roughly understood as a neural network structure containing multiple hidden layers. In order to improve the training effect of deep neural networks, people make corresponding adjustments to the connection method and activation function of neurons. In fact, there were many ideas in the early years, but due to insufficient training data and backward calculation ability, the final results were not satisfactory.
Deep learning has achieved various tasks like a ruin, making it seem that all machine-assisted functions are possible. Driverless cars, preventive medical care, and even better movie recommendations are all around the corner or will soon be realized.
The difference and connection of the three
Machine learning is a method to realize artificial intelligence, and deep learning is a technology to realize machine learning. We use the simplest method-concentric circles, to visually show the relationship between the three.
Figure 3 Schematic diagram of the relationship between the three
At present, the industry has a common sense of error that " deep learning may eventually eliminate all other machine learning algorithms ." This awareness is mainly due to the fact that the application of deep learning in computer vision and natural language processing far exceeds traditional machine learning methods, and the media has exaggerated reports on deep learning.
Deep learning, as the hottest machine learning method at present, does not mean that it is the end of machine learning. At least the following problems currently exist:
1. Deep learning models require a lot of training data to show magical effects, but in real life, small sample problems are often encountered. At this time, deep learning methods cannot be used, and traditional machine learning methods can handle them;
2. In some fields, the traditional simple machine learning method can be used to solve it well, and it is not necessary to use complex deep learning methods;
3. The idea of deep learning is inspired by the human brain, but it is by no means a simulation of the human brain. For example, after showing a three or four-year-old child a bicycle, he will see a bicycle with a completely different appearance again. In all likelihood, it can be judged that it is a bicycle. That is to say, the human learning process often does not require large-scale training data, and the current deep learning method is obviously not a simulation of the human brain.
When deep learning tycoon Yoshua Bengio answered a similar question on Quora, there was a paragraph that was particularly good. Here is a quote to answer the above question:
Science is NOT a battle, it is a collaboration. We all build on each other's ideas. Science is an act of love, not war. Love for the beauty in the world that surrounds us and love to share and build something together. That makes science a highly satisfying activity, emotionally speaking!
The general meaning of this passage is that science is not war but cooperation. The development of any discipline is never a road to black, but peers learn from each other, learn from each other, learn from each other, and complement each other, standing on the shoulders of giants. Forward. The same is true for machine learning research. Life and death is a cult, and openness and tolerance is the right way.
Combining with the development of machine learning since 2000, I am deeply impressed by Bengio's words. Entering the 21st century, looking at the development of machine learning, research hotspots can be simply summarized as manifold learning from 2000 to 2006, sparse learning from 2006 to 2011, and deep learning from 2012 to present. Which machine learning algorithm will become a hot spot in the future? Wu Enda, one of the three giants of deep learning, once said, “After deep learning, transfer learning will lead the next wave of machine learning technology”. But in the end, who is the next hot spot for machine learning?