Welcome to the Weizmann practical Deep Learning Course 2024
All communication with the lecturers will be made via SLACK. Join here:
Your lecturers and TAs are
Etienne Dreyer, Nilotpal Kakati, Dmitrii Kobylianskii and Prof Eilam Gross.
The grading system is based on your mandatory homework assignments (10%), a project (<30%), and a take-home assignment (>60%). The exact weight of the project and take-home assignment will be fixed so the class average will not exceed 90.
All lecture slides and tutorial code will be posted below.
| Date | Lecture | Slides & Video |
Tutorial | Slides & Video |
Tutorial 2 | Slides & Video |
|---|---|---|---|---|---|---|
| 18/4/2024 |
Eilam: Introduction |
Etienne: Python essentials |
|
Etienne: NumPy and grad. desc. |
||
| *2/5/2024 |
Dmitrii: Backpropagation |
Nilotpal: pytorch (tut) |
Nilotpal: homework 1 Classification |
|||
| 9/5/2024 |
Eilam: Convolutional NN |
Nilotpal: CNNs (tut) |
Dmitrii: Optimisation, |
|||
| *16/5/2024 |
Etienne: Autoencoders |
Nilotpal: VAE (tut) |
Etienne: transfer learning homework 2 |
|||
| 23/5/2024 |
Eilam: CNN architectures and RNN |
Eilam: GAN |
Nilotpal: DCGAN tutorial |
|||
| **30/5/2024 |
Nilotpal: Attention is All You Need |
Eilam: Attenion on Attention |
Eilam: |
Nilotpal: Attention tutorial |
notebook | |
| **6/6/2024 |
Eilam: Detection & Segmentation |
Nilotpal: UNET
|
notebooks |
Dmitrii/Nilotpal: Homework 3: |
||
| *^13/6/2024 |
Eilam (zoom?): Graph Neural Networks |
Etienne: GNN tutorial |
Etienne: homework 4: Graph Neural Networks |
|||
| 20/6/2024 |
Nilotpal: Diffusion |
Dmitrii: Diffusion tutorial |
Nilotpal: Bayesian NN |
|||
| 27/6/2024 |
Eilam: Deep Reinforcement Learning |
Dmitrii: Deep Q-learning tutorial
|
Etienne: Homework 5: policy gradient |
|||
| 4/7/2024 | Project Proposals I | |||||
| 11/7/2024 | Project Proposals II. | |||||
|
16/7 10:00-12:00 |
Final exam | |||||
|
19/08 11:00-16:00 |
Project Presentations (POSTERs festival) |