Dr. Abdelghafour Halimi
AI & Data Science Expert, KAUST
Abstract
This workshop provides a fast, structured, and practical introduction to Machine Learning and Deep Learning by combining real-world intuition with real-time interactive demos. Participants will learn how to distinguish ML from DL, understand the main learning paradigms and core modeling concepts, follow the end-to-end ML workflow, and connect key ideas to real-world applications. The session will cover essential concepts such as data splitting, generalization, overfitting and underfitting, neural network fundamentals, loss functions, optimizers, and the intuition behind backpropagation. These concepts will be illustrated through live, interactive demonstrations designed to make the learning experience practical and engaging. The session concludes with an interactive quiz to reinforce the main takeaways. By the end of the workshop, participants will be able to differentiate ML and DL, understand the main ML workflow and learning paradigms, explain core modeling concepts, and understand the fundamentals of neural network training.
Biography
Dr. Abdelghafour Halimi is an AI and Data Science expert currently working at KAUST, with expertise in machine learning, deep learning, computer vision, image processing, and scientific AI applications. He holds an M.S. and a Ph.D. in Artificial Intelligence and Image Processing from the National Polytechnic Institute of Toulouse, France, completed in 2014 and 2017, respectively. With more than 10 years of experience in AI across research and industry, he previously served as a Research Assistant at Pierre Fabre from 2014 to 2017 and as a Data Scientist at ATOS from 2018 to 2023. He has also contributed to collaborative projects involving major organizations such as CEA, Airbus, CNES, and the European Space Agency (ESA). His work spans multiple application areas, including remote sensing, medical imaging, computer vision, and scientific data analysis. More information: www.ahalimi.com
Seats are limited
Tutorials run on Monday, 26 October 2026 at KAUST. Attendance is free, but registration is required.
