An assistant professor exploring the intersection of artificial intelligence, robotics, and pedagogy at the University of Toronto.
Specialized in artificial intelligence and robotics. Research focused on computer vision and reinforcement learning for autonomous systems.
Focus on software systems, machine learning, and artificial intelligence.
Teaching courses in artificial intelligence, robotics, and machine learning. Developed innovative pedagogical approaches including interactive learning platforms. Mentoring undergraduate and graduate students in research projects.
Conducted research on visual perception and scene understanding using deep learning. Published findings in top-tier computer vision conferences.
Core principles of artificial intelligence with applications to robotics. Topics include search and planning methods, logical reasoning, knowledge representation, probabilistic inference, and learning approaches for intelligent robotic systems.
Foundational machine learning methods with mathematical and algorithmic focus. Topics include supervised and unsupervised learning, neural networks, dimensionality reduction, model evaluation, and an introduction to reinforcement learning.
Computer hardware and system architecture from the digital logic level upward. Covered instruction set architectures, assembly programming, memory systems, datapaths, and control, with emphasis on low-level performance and correctness.
Design and analysis of efficient data structures and algorithms. Topics include asymptotic complexity, balanced trees, hashing, heaps, graph algorithms, and amortized analysis.
Mathematical foundations for robotics and autonomous systems. Topics include optimization, probability and stochastic processes, signals and filtering, numerical methods, and applications to perception, planning, and control.