| Topic 1 |
Introduction to Word Embeddings |
Language Models, word2vec, FastText |
π₯ PDF |
| Topic 2 |
Transformers |
Intro to BERT, attention mechanism, encoder part, masked attention, cross attention, decoder part |
π₯ PDF |
| Topic 3 |
LLMs in Practice Adapting Foundation Models |
Retrieval-augmented generation with LLM, Zero-shot Learning, Few-shot Learning, CoT, Fine-Tuning (Feature extraction, Full fine-tuning, Multi-stage fine-tuning, Adapter fine-tuning) and Domain Adaptation, Self-Supervised |
π₯ PDF |
| Topic 4 |
Practical Concerns for Machine Learning |
Generalization, Ensemble Methods, Imbalanced Dataset handling |
π₯ PDF |
| Topic 5 |
Modern Computer Vision Architectures |
From CNNs to Transformers |
π₯ PDF |
| Topic 6 |
Video Classification |
Late Fusion, Early Fusion, 3D CNN, Two-Stream Networks, I3D |
π₯ PDF |