Chalmers Machine Learning Seminars

This is where we will keep information about the Machine Learning Seminar Series at Chalmers. The seminars are open to the public, and we encourage people to join us. The focus of these seminars are machine learning in general, including Deep Learning and Bayesian methods. We intend to host seminars that are accessible to a broader spectrum of attendants, working in different fields of science, but with an interest in machine learning.


The seminar series is currently on summer break. We will resume in August or early September. Keep yourself updated with our Google calendar or our mailing list!

We meet every week at Thursdays 10:30 in the EDIT-room (3364) at Hörsalsvägen 11, Gothenburg, Sweden.

See below for the planned seminars, and click the “plus” to add this to your Google calendar.

To import the seminar calendar, please use the following ICS link, or view the HTML version.

Mailing list

Announcements are posted in our mailing list,, which is free for anyone to join. Click here for more info.


In the near future we intend to cover topics such as batch normalization, generative adversarial networks, domain adaptation, and attention models.

Suggestions on speakers and topics can be made to the mailing-list (see above).

For questions and suggestions, please contact

Resources from previous seminars

  • 2016-10-27: Mehdi Ganimifard
    Slides (google docs).
  • 2016-09-29: Breakthroughs in Neural Machine Translation
    Speaker: Olof Mogren
    Slides and related reading.
  • 2016-09-22: ACL 2016 Overview
    Speaker: Olof Mogren
  • 2016-03-03: Reducing structured prediction to classification
    Speaker: Richard Johansson
  • 2016-02-18: Neural Attention Models
    Speaker: Olof Mogren (mogren at chalmers dot se).
    Slides and related reading.
  • 2016-02-11: What would have happened if…? ML and causal inference
    Speaker: Fredrik Johansson (frejohk at chalmers dot se).
  • 2016-02-04: Go solved by Google!? How Google Deep Mind were able to beat a professional Go player using deep reinforcement learning.
    Speaker: Mikael Kågebäck (kageback at chalmers dot se).
  • 2016-01-28: Provable Bounds for Learning Some Deep Representations
    Speaker: Ashkan Panahi (ashkanp at chalmers dot se).