Deep Learning
| Unit | Topic | Materials |
|---|
| 01 | From Linear Models to Neural Networks | Slides |
| 02 | Backpropagation and Automatic Differentiation | Slides |
| 03 | Deep Neural Networks | Slides |
| 04 | Optimization Algorithms and Learning Rates | Slides |
| 05 | Training Stability and Normalization | Slides |
| 06 | Regularization and Training Diagnostics | Slides |
| 07 | Convolutional Neural Networks | Slides |
| 08 | Deep Convolutional Architectures and Residual Learning | Slides |
| 09 | Data Augmentation and Transfer Learning | Slides |
| 10 | Object Detection | Slides |
| 11 | Semantic Segmentation | Slides |
| 12 | Sequence Modeling and Recurrent Neural Networks | Slides |
| 13 | Long-Term Dependencies, Gating, and Encoder–Decoder Models | Slides |
| 14 | Attention and Self-Attention | Slides |
| 15 | Transformer Architecture and Computation | Slides |
| 16 | Vision Transformer | Slides |
| Supplement | Information Theory Fundamentals | Slides |
Language Models
| Unit | Topic | Materials |
|---|
| 01 | Language Modeling and Statistical Foundations | Slides |
| 02 | Word Embeddings and Neural Language Models | Slides |
| 03 | Conditional Language Models and Sequence Generation | Slides |
| 04 | Pretrained Language Models | Slides |
| 05 | Adapting and Using Large Language Models | Slides |
Generative Models
| Unit | Topic | Materials |
|---|
| 01 | Generative Modeling and Autoencoder Representations | Slides |
| 02 | Latent Variable Models and Variational Autoencoders | Slides |
| 03 | Generative Adversarial Networks | Slides |
| 04 | Normalizing Flows and Invertible Density Transformations | Slides |
| 05 | Diffusion Models: Adding Noise, Learning, and Sampling | Slides |
| 06 | Conditional Diffusion and Latent Space Generation | Slides |
| 07 | Continuous Generation and Flow Matching | Slides |
| 08 | Generative Model Evaluation and Frontier Issues | Slides |
3D Vision
Covered topics include ray tracing of volume densities, EWA volume splatting, NeRF, and 3D Gaussian Splatting.