RezaAzad

Reza Azad

KU Leuven and Huawei research center

Title:Few-shot Continual Learning
Abstract

In this lecture, we will talk and discuss two new hot topics in machine learning, namely few-shot and continual learning. In few-shot learning, we are dealing with a few labelled data. The learning algorithm in here needs to be trained in a way to have generalization performance with the limited data. To overcome this challenge, we will discuss the Prototypical Network approach for few-shot classification. Furthermore, we will discuss how the human brain learns to keep knowledge and continually improve its knowledge. Based on this assumption, we will present the Elastic Weight Consolidation approach as a way to keep the knowledge inside the model and avoid catastrophic forgotten.

Bio

Reza Azad is going as a Ph.D. student under the supervision of Prof. Tinne Tuytelaars at the most prestigious Katholieke Universiteit Leuven (KU Leuven), Belgium and a Research Fellow at Huawei Research Center in Belgium. His doctoral research focuses on deep continual learning. He continuously seeks for research ideas to model human cognition in machine learning algorithms. With an excellent career in academics and research, he also received his M.Sc. Degree from the Sharif University of Technology in Iran.