Machine learning, deep learning, … When you try to start learning AI there are lot of terms, concepts and methods. It can be complicated to understand what to start with.
Today I’ll help you with this quick introduction.
AI, Deep learning and machine learning are not synonym…
AI a big family !
People often think that these words are the same. There is some link between them but there are not synonym.
Artificial intelligence is the root concept. It’s divided into two categories, Weak AI and strong AI.
The weak AI regroup all methods, algorithms, … which simulate certain mechanisms of the human brain to solve problems.
Strong AI is dedicated to the system that can work like the humain brain, it’s not just simulation. Currently, there is no official solution that fit to this category.
Weak AI
Machine learning is one of famous weak AI solutions. This concept has been introduced by Arthur Samuel in 1952. It qualifies a machine with the abilities to take decisions. A big part of these machines has been inspired by the functioning of the human brain.
As you can see this concept is not new but stay hard to define. Here are two famous definitions I like.
Machine learning is the science of getting computers to act without being explicitly programmed — Stanford
_Machine Learning at its most basic is the practice of using algorithms to parse data, learn from it, and then make a determination or prediction about something in the world.” — _Nvidia
There are two types of ML (Machine learning) problems.
Supervised Machine learning algorithms
In this type of algorithms we have some features (or inputs) **X **and a result (or output) y. The goal of these algorithms is to predict y in function of some inputs.
You can split supervised algorithms in two categories.
#data-science #artificial-intelligence #machine-learning #algorithms #deep-learning
