DMS - Drone Meteorite System

What is Machine Learning?

In the early days of artificial intelligence, the field rapidly tackled and solved problems that are intellectually difficult for human beings but relatively straightforward for computers – problems that can be described by a list of formal, mathematical rules. The true challenge to artificial intelligence proved to be solving the tasks that are easy for people to perform but hard for people to describe formally – problems that we solve intuitively, that feel automatic, like recognizing spoken words or faces in images. This meant that AI systems needed the ability to acquire their own knowledge, by extracting patterns from raw data. This capability is known as machine learning.

Machine learning isthe futureinsightfulcreativethe pathto Artificial Intelligence

Deep Learning

For problems that are too complex to be solved using simple “linear” models used in Machine Learning, we make use of deep learning. Previously known by other names, deep learning is so called because of the architecture of the mathematical functions, or “convolutional layers,” that are used to process the given data and produce an output.

Deep learning models are created using Neural Networks, which are generally made up of several layers; the number of layers, or “depth”, increases with the complexity of the application of the deep learning model.

Different types of neural network architectures have been built for a variety of applications. At the Sharjah Center for Astronomy and Space Sciences, since our applications deal with visual data, i.e., images and videos, we use Convolutional Neural Networks (CNNs) as they are best suited for applications involving computer vision.