Arvutiteaduse instituut
  1. Kursused
  2. 2019/20 sügis
  3. Special Course in Machine Learning: Fast.ai (MTAT.03.317)
EN
Logi sisse

Special Course in Machine Learning: Fast.ai 2019/20 sügis

  • Main
  • Schedule
  • Submission
  • Links

Lecture schedule

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)

Deep Learning from the Foundations:

  • 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)
  • Arvutiteaduse instituut
  • Loodus- ja täppisteaduste valdkond
  • Tartu Ülikool
Tehniliste probleemide või küsimuste korral kirjuta:

Kursuse sisu ja korralduslike küsimustega pöörduge kursuse korraldajate poole.
Õppematerjalide varalised autoriõigused kuuluvad Tartu Ülikoolile. Õppematerjalide kasutamine on lubatud autoriõiguse seaduses ettenähtud teose vaba kasutamise eesmärkidel ja tingimustel. Õppematerjalide kasutamisel on kasutaja kohustatud viitama õppematerjalide autorile.
Õppematerjalide kasutamine muudel eesmärkidel on lubatud ainult Tartu Ülikooli eelneval kirjalikul nõusolekul.
Courses’i keskkonna kasutustingimused