Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.
Explores the evolution of image representation, challenges in supervised learning, benefits of self-supervised learning, and recent advancements in SSL.
Explores socially-aware AI for last-mile mobility, focusing on understanding social etiquettes, anticipating behaviors, and forecasting crowd movements.
Explores the learning dynamics of deep neural networks using linear networks for analysis, covering two-layer and multi-layer networks, self-supervised learning, and benefits of decoupled initialization.
Explores non conceptual knowledge systems through image translation, video synthesis, self-supervised learning challenges, and universal representations.
Delves into the spectral bias of polynomial neural networks, analyzing the impact on learning different frequencies and discussing experimental results.
