Artificial Intelligence – Machine Learning – Deep Learning

By: Nunung Nurul Qomariyah, Ph.D

We often heard about these three terms being used in the media as a fascinating technology produced in this century. What really makes them different? Are they referring to the same concepts?

I found a lot of interchanged usage of terms out there. Even Computer Science students still get mixed up with the terms. A commonly perpetuated myth is that Machine Learning,  AI and Deep Learning being the same thing. Mainstream media might have confused you, but these are three different things. However, those three are closely associated. Let’s have a look at some definitions.

Artificial Intelligence (AI)

AI is a computer system capable of making decisions based on learning. An AI ‘trains’ on input datasets and learns via mathematical algorithms to make correct decisions. It requires human intervention during the training. As it tries to mimic human behaviour, it also learns about how the human receive information, i.e. through their eyes (computer vision), through their language (natural language processing), also through their past moments  which is stored in their memory (machine learning).

Machine Learning (ML)

ML algorithm powers the AI. It enables a computer to learn without being explicitly programmed. We can say that Machine Learning is a small subset of Artificial Intelligence. It uses logical and statistical approach to enable machines to improve with experiences.  There is one algorithm in this area which try to imitate how the brain cell work, which is called Neural Network. This algorithm is used as the base of the Deep Learning field.

Deep Learning (DL)

Subset of ML which make the computation of multi-layer neural network more feasible and make use of high speed computer processing power. The most common implementation of Deep Learning is in the area of Computer Vision.

References:

• Russel, S., & Norvig, P. Artificial Intelligence: A modern approach, 2016. EUA: Prentice Hall