How can I attend lectures and lab sessions?

ADA will be run as a hybrid offline/online course: Lectures (Wed 8:15-10:00) will take place in the Rolex Forum. One third of students will be allowed to attend in person. Additionally, the lectures will be live-streamed on Zoom, as well as recorded and made available here on the course website. Lab sessions (Fri 13:15-15:00) will be held online only.

Lecture recordings will be posted in the website every Thursday (the day after the lecture) EOD!

For details on how to connect via Zoom, please refer to the communication guidelines!

Tutorials and Homeworks

Tutorials on Github (TBD)

Homeworks on Github (TBD)

Project

Lecture schedule

Week Lecture Date Lecture Lab Session
1 16 Sep 2020 Intro [slides] [recording] Intro to tools [project intro] [lab sessions intro] [projects video] [git basics video]
2 23 Sep 2020 Handling data [slides] [recording] Handling data [github]
3 30 Sep 2020 Visualization  
4 07 Oct 2020 Read the stats carefully  
5 14 Oct 2020 Regression analysis  
6 21 Oct 2020 Observational studies  
7 28 Oct 2020 Supervised learning  
8 04 Nov 2020 Applied ML  
9 11 Nov 2020 Unsupervised learning  
10 18 Nov 2020 Handling text  
11 25 Nov 2020 Handling text  
12 02 Dec 2020 Handling networks  
13 09 Dec 2020 Scaling up  
14 16 Dec 2020 ADA in action  


Important Dates

  • Homework
    • Homework H1
      • Release: 02 Oct 2020
      • Due: 16 Oct 2020
    • Homework H2
      • Release: 6 Nov 2020
      • Due: 20 Nov 2020
  • Project deliverables
    • Project Milestone P0
      • Due: 02 Oct 2020
    • Project Milestone P1
      • Due: 23 Oct 2020
    • Project Milestone P2
      • Due: 06 Nov 2020
    • Project Milestone P3
      • Due: 27 Nov 2020
    • Project Report
      • Due: 18 Dec 2020
  • Final exam (TBA)

All deadlines are 23:59 CET

Contact

The main channel for class-related communication is Zulip. For best practices regarding course-related communication, please read the communication guidelines.

Zulip server: https://ada2020zulip.epfl.ch

Instructor

Teaching assistants (TAs; PhD students)

  • Akhil Arora
  • Anastasiia Kucherenko
  • Daniyar Chumbalov
  • Ekaterina Svikhnushina
  • Halima Schede
  • Kristina Gligorić
  • Lars Klein
  • Manoel Horta Ribeiro
  • Tiziano Piccardi
  • Valentin Hartmann

Student assistants (SAs; MS students)

  • Davit Martirosyan
  • Germain Zouein
  • Jonathan Labhard
  • Kuan Tung
  • Oliver Cloux
  • Pablo Cañas Castellanos
  • Stefano Huber
  • Sylvain Lugeon
  • Yann Bouquet
  • Yann Yasser Haddad


Resources