Neural Networks
Basic concepts of neural networks
Deep NNs
Fundamentals of deep architectures and multilayer networks
CNNs
Models specialized in processing images and spatial data
RNNs & Attention
Models for sequential data and the mechanisms that allow networks to focus on relevant information
Transformers
Models based on self-attention, widely used in NLP and computer vision
Diffusion Models
Generative models that iteratively transform noise into realistic data such as images
Graph NNs
Models tailored to process and learn from complex, graph-structured data
Information Theory
Literature
Key research papers, influential readings, and my thesis
Feedback
Questions, corrections, and discussion about the notes.