Dl2023

| Week | Lecture notebooks | Supplementary materials | Homework | Seminars | |:------:|:----------|:----------:|:----------:|-------| |1| Lecture 1. Deep learning basics [GitHub] <br> Lecture 2. Convolutional neural networks [GitHub] <br> Lecture 3. Training better [GitHub]| | HW1 <br> (Deadline: April, 14, 2023, 23:59 MSK) | Seminar 2 <br> Seminar 3: logging practice and regularizations examples| | 2 | Lecture 4. CV tasks [GitHub] <br> Lecture 5. Modelling sequences [GitHub] <br> Lecture 6: Vision Transformers [GitHub] | | | Seminar 4: object detection and semantic segmentation + solution demos | | 3 | Lecture 7. Graph Neural Networks [GitHub] <br> Lecture 8. General tricks for efficient training [GitHub] <br> Lecture 9. Training large models [GitHub] | | | | 4 | Lecture 10. Contrastive learning / self-supervised learning [GitHub] <br> Lecture 11: One-shot/Zero-shot/Few-shot learning [GitHub] <br> Lecture 12: Adversarial attacks and training [GitHub] | | HW2 <br> (Deadline: May, 1, 2023, 23:59 MSK) | | 5 | Lecture 13: Generative models I (Autoregressive models and VAE) [GitHub] <br> Lecture 14: Generative models II (Generative adversarial models) [GitHub] <br> Lecture 15: Generative models III (Score-based and diffusion models) [GitHub] | | HW3 <br> (Deadline: May, 17, 2023, 23:59 MSK) | Seminar 8. VAE |