What is Artificial Intelligence?
Unless you’ve been living under a rock, you’ve probably have heard about artificial intelligence and other subcategories such as machine learning and deep learning. At the first glance such terms might be quite overwhelming specially for those whose major is not related to computer sciences or mathematics. My name is Amir Panahi and, in this post, I’m going to explain the core concepts of artificial intelligence, machine learning and deep learning for you guys as simple as possible. If you are interested in such technologies or might even want to try them yourself in your research, or just for fun, this is for you.
Artificial Intelligence Definition
While there are different definitions of artificial intelligence, the general definition provided by IBM is that AI tries to mimic the decision making and problem-solving power of human intelligence. Whenever scientists try to make a machine to perform a task that requires humans intelligence, there is a trace of artificial intelligence and machine/deep learning.
But here we go again! what is AI really?! Those definitions might start to make sense if I give you a tangible example here. Imagine you have a list of houses, their sizes and related prices in a specific area (which is called “dataset”). By using a machine learning algorithm (more about this later) you can create a model and train that model (using those existing variables such as prices, sizes, etc.) and later on you can use that same model to predict the price of a house that is not even listed in the dataset. So simply put, you can predict almost any feature of subject with high accuracy (let it be a student mark in an exam, a car price, or a house price) if you provide and train the model with enough data and examples.
That was just a very simple application of Narrow AI and Machine Learning. But it can get too complex too soon when you get to General AI. You can train a model to understand human speech, or to recognize faces and objects using Deep Learning
Artificial intelligence has different branches such as machine learning and deep learning. In the above example we discussed machine learning. Deep learning on the other hand is actually a subfield of machine learning that uses artificial neural networks to mimic the structure of brain to get to touch more features from the input. Examples of deep learning are chatbots, virtual assistants, facial recognition, speech recognition and so on.
I hope you enjoyed the post so far. In the future posts I will cover the definition and applications of artificial intelligence, machine learning and deep learning in different fields with more details and examples.
Please let me know what you think about artificial intelligence and what has been your experience of such technologies in the comment section below.
Link to IBM could education post about AI: