Teaching
In Winter 2024, I will teach the machine learning and conversational AI courses.
Conversational AI (COMP 499/691, Concordia University)
Winter 2022, Winter 2023
Advancing artificial intelligence to enable machines to engage in natural, human-like conversations represents a significant breakthrough. Conversational AI, which encompasses the technology for human-machine communication, is evolving rapidly and has attracted substantial investment from both tech giants and startups.
This course offers a comprehensive understanding of conversational AI, with a primary focus on how modern deep learning technologies are utilized to create advanced speech assistants and large language models. It is designed for graduate and advanced undergraduate students specializing in AI and machine learning, equipping them with the necessary skills to develop cutting-edge conversational AI systems. This course also complements Concordia University's existing AI courses, enhancing its educational offerings in this domain.
In addition to traditional lectures, this course incorporates practical elements such as lab sessions, tutorials, and hands-on projects in conversational AI using the popular SpeechBrain toolkit.
See more info here.
Machine Learning (COMP 432/6321, Concordia University)
Winter 2022, Winter 2023
This course introduces conceptual and practical aspects of machine learning. It will start with an introduction to fundamental machine learning concepts and learning modalities. It will then discuss supervised machine learning models such as linear models, neural networks, support vector machines, decision trees, and ensemble methods. Finally, the course will introduce some unsupervised learning techniques, such as clustering and feature reduction. For each topic, lab sessions are proposed to help students familiarize themselves with the practical implementation of the techniques discussed during the lectures. Beyond the theoretical part, students are asked to work on an actual machine learning project. A mid-term and a final exam will be done.
See more info here.
Winter 2021
This is a course offered by Mila and the Université de Montréal in the context of the professional master in machine learning. It can be attended by the master students in computer science as well.
The goal of this course is to prepare master students to work on real machine learning projects. This course is thus designed to connect the theoretical aspects of deep learning with strong practical and coding insights. Having strong theoretical and coding capabilities, in fact, is essential for the students to succeed in their future careers as machine learning developers.
The first part aims to give the students the basic tools needed to work on real machine learning projects. We will start with some lectures on Linux, HPC cluster usage, git, Colab, PyTorch, deep learning trips and tricks.
In the second part, students will work on real machine learning projects. Students will be assigned to one of the proposed project and they will work in small groups of 2-6 students. During this phase, the progress of the project is constantly monitored by the teacher and the teaching assistants.
At the end of the course, we expect that students will provide a short report summarizing the main achievements. An oral presentation in front of the teachers and the classmates is required as well.
See more info here.