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 the Restricted Boltzmann Machine, a more expressive version of the Boltzmann Machine with hidden units.
Covers non-linear dimensionality reduction techniques using autoencoders, deep autoencoders, and convolutional autoencoders for various applications.
Introduces the basics of data science, covering decision trees, machine learning advancements, and deep reinforcement learning.
Discusses challenges in AI systems, supervised learning limitations, and the necessity of data-driven methods in reinforcement learning.
