Covers the foundational concepts of deep learning and the Transformer architecture, focusing on neural networks, attention mechanisms, and their applications in sequence modeling tasks.
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 material lifecycle, properties, sustainability, and design, emphasizing the importance of auditing products for sustainability and discussing the evaluation of consumer products like LEGO.
