AI? ML? DL?
Artificial intelligence (AI), machine learning (ML) and deep learning (DL) are three terms often used interchangeably nowadays. However, it might make people confused about the key distinctions among them. To better explain about these three terms, just think of a set of Russian dolls. When you open a large one, there’s a smaller one inside, and so on. Deep learning is a subset of machine learning, and machine learning is a subset of AI (See Figure 1).
In other words, AI can be viewed as an umbrella term for the other two terms, which means, all ML is AI, but not all AI is ML.
Figure 1: History of AI, ML, and DL
Artificial Intelligence (AI)
John McCarthy (Figure 2), widely recognized as one of the fathers of AI, defined AI as “the science and engineering of making intelligent machines.” Within decades, AI is the amazing language all over mathematics, statistics, industries and our fantasies about the future.
There are a lot of ways to describe AI, but in general, it is the intelligence demonstrated by machines rather than humans or animals. Image a computer system which is able to perform tasks that normally require human intelligence, for example, speech translation, fraud detection, face recognition… etc. The above applications are all based on AI. To simulate human intelligence, machine learning and deep learning algorithms are then rise up.
Figure 2: John Mccarthy – the Father of AI
What about ML and DL?
Briefly, machine learning are programs that can alter themselves and does not require human intervention to make certain changes; while deep learning are algorithms that can provide more accuracy and higher performance compared to machine learning. Both of them need lots of math and computing, moreover, deep learning even uses a layered structure of algorithms. More details about machine learning and deep learning will be discussed in our next article.