Deep learning For Perception

Catalog description

This course exposes the students to the mathematical foundations of deep learning applied to images . Perception stacks in state-of-the-art robots are rapidly adapting the latest advancements in deep learning due to their efficacy and high accuracy. These deep learning - based methods are also accelerable using parallelized hardware such as GPUs that can enable low latency operations of complex tasks such as real-time scene segmentation. T he students will be train ed in formulat ion , develop ment and implement ation of deep learning solutions for common computer vision problems in the context of robot perception. The course will cover advanced and state-of-the-art topics such as sim2real, adversarial attacks on neural networks, vision transformers and d iffusion m odels. Additional topics explored in this course include image formation, linear classifiers, n eural networks and backpropagation, Convolutional Neural Networks (CNNs), CNN a rchitectures, d ata generation for sim2real, black - and w hit e-box a ttacks on n eural n etworks as applied to build state-of-the-art robotic stack . S tudents will gain knowledge about the considerations required to enable a robotic system with the state-of-the-art deep learning toolkit. The course is designed to balance theory with applications through projects. Recommended Background: Proficiency in p rogramming (Preferably in Python ) , multi-variate c alculus (MA1024) , l inear a lgebra (MA2071/2072) , and p robability (MA 2621/2631 ) .