Seminars are held every week on Thursday at 14.15 - 16.00 Liivi 2 - 512 (starting from 12.09).
For each new lecture, watch it at home, be prepared to answer questions related to the material presented in a lecture and click-through jupyter notebooks associated with lecture.
Please, choose a lesson that you will moderate and homework/test for which you will prepare here.
Practical Deep Learning for Coders (v3):
- 12.09 - Introduction and course organization and Lesson 1: Image classification (Dima and Tambet)
- 19.09 - Lesson 2: Data cleaning and production; SGD from scratch (Mikhail)
- 27.09 - Lesson 3: Data blocks; Multi-label classification; Segmentation (Hannes, PDF)
- 03.10 - Lesson 4: NLP; Tabular data; Collaborative filtering; Embeddings (Lisa & Lisa Y, PDF)
- 10.10 - Lesson 5: Back propagation; Accelerated SGD; Neural net from scratch (Andreas, google slides)
- 17.10 - Lesson 6: Regularization; Convolutions; Data ethics (Mariia & Mohammed, google slides)
- 24.10 - Lesson 7: Resnets from scratch; U-net; Generative (adversarial) networks (Laura & Roman, google slides)
- 31.10 - Lesson 8: Matrix multiplication; forward and backward passes (Miki, PDF)
- 07.11 - Lesson 9: Loss functions, optimizers, and the training loop (Viacheslav & Novin, google slides)
- 14.11 - Lesson 10: Looking inside the model (Sten & Joonas, PDF)
- 21.11 - Lesson 11: Data Block API, and generic optimizer (Enes)
- 28.11 - Lesson 12: Advanced training techniques; ULMFiT from scratch (Maher, google slides)