Introduction

Following the resounding success of 2019 Summer School, CISIR-HICoE is pleased to bring back the Summer School: Machine Learning and Deep Learning Applications this year but in virtual setting due to the current unsettling situation with COVID-19.

This year Summer School will be held on 3, 10, 17 and 24 September, 2020, via Microsoft Teams platform. This annual program is organized by Center for Intelligent Signal and Imaging Research (CISIR), National Higher Institution Centre of Excellence (HICoE).

Additionally, we want to facilitate exchange and sharing between local and international researchers in view of upcoming collaboration and funding opportunities. The 2020 Summer School will bring together leading experts to educate and foster collaboration among the next generation of researchers. This program will enable students, academic researchers and industrial practitioners to realize the exciting possibilities surrounding the use of machine learning and deep learning in real-world applications.

Scope and goals

At Summer School, we will discuss on how to implement machine learning algorithm and deep learning framework in various application focusing on images and signals. School participants will learn methods and techniques that are crucial for understanding current research in machine learning. They will also have an opportunity for hands-on code execution, learn modern stochastic optimization methods and regularization techniques for neural networks.

Course Highlights

• What is deep learning and why is it so popular?

• What is the difference between machine learning and deep learning?

• What are the best computing resources to consider for deep learning training/inference (cloud GPU - AWS, Azure, GCP, Paperspace, FloydHub or local server)?

• How to setup your very first deep learning framework and dependencies (virtual environment, anaconda, docker)?

• How to implement machine learning algorithms and deep learning frameworks in real-world applications (supervised/unsupervised classification, conventional/ medical image segmentation, time-series signal processing)?