How to define this terms "machine learning", "deep learning", and "AI"?

          Machine learning is a group of  algorithms that train on a data set to make predictions or take actions in order to optimize some systems.

    for example , oversee classification algorithms are used to classify prospect clients into good or bad prospects, for loan purposes, based on historical data. The techniques involved, for a given task (e.g. supervised clustering), are varied: naive Bayes, SVM, neural nets, ensembles, association rules, decision trees, logistic regression, or a combination of many.

      All of this is a subset of data science. When these algorithms are automated, as in automated piloting or driver-less cars, it is called AI, and more specifically, deep learning. If the data collected comes from sensors and if it is transmitted via the Internet, then it is machine learning or data science or deep learning applied to IoT. Artificial intelligence.

      Some people have a various definition for deep learning. They consider deep learning as neural networks (a machine learning technique) with a deeper layer.

      AI (Artificial intelligence) is a subfield of computer science, that was created in the 1960s, and it was (is) concerned with solving tasks that are easy for humans, but hard for computers. especially, a so-called Strong AI would be a system that can do anything a human can (perhaps without purely physical things). This is fairly generic, and contain all kinds of tasks, like planning, moving around in the world, recognizing objects and sounds, speaking, translating, performing social or business transactions, creative work (making art or poetry), etc.

     NLP (Natural language processing) is frugally the part of Artificial intelligence that has to do with language (usually written). Natural language processing Machine learning.

     Machine learning is involved with one part of this: given some  Artificial intelligence problem that can be described in discrete terms and given a lot of information about the world, discover what is the “correct” action, without having the programmer program it in. 

     Usually several outside process is needed to judge whether the action was correct or not. In mathematical terms, it’s a function: you feed in some input, and you want it to manufacture the right produce, so the whole problem is artlessly to build a sample of this mathematical function in some automatic way. 

   To sketch a uniqueness with Artificial intelligence, if I can write a very intelligent program that has human-like conduct, it can be Artificial intelligence , but unless its parameters are automatically learned from data, it’s not machine learning. 


    Deep learning is one type of machine learning that’s very popular now. It includes a particular kind of mathematical model that can be thought of as a composition of straightforward blocks (function composition) of a certain type, and where some of these blocks can be regulate to better predict the final result.

    Inspired by the previous example of successful learning, let  pretend a model machine learning task. assume we would like to program a machine that learns how to filter spam e-mails.  

    Unsophisticated solution would be seemingly similar to the way rats learn how to evade poisonous baits. The machine will frugally protect all previous e-mails that had been labeled as spam e-mails by the human user.

    When a new e-mail arrives, the machine will search for it in the set of former spam e-mails. If it matches one of them, it will be trashed. do it another way, it will be moved to the user's inbox folder.