Dear all,

We kindly invite you to our seminar series ‘Deep learning in brains and machines’, run at the TU this winter semester.

Time: Mondays from 10:15 - 11:45
Location: TU Berlin, room 5.006, Marchstrasse 23
First meeting: 21 Oct 2019

Deep learning has received most attention for the enormous advances in engineering and gaming applications, but it is also becoming a standard research tool in neuroscience and cognitive science. The aim of the seminar is to provide an overview over recent work that uses deep learning to understand the algorithms used by the brain.

Topics include: 1) convolutional networks as models for sensory systems, 2) recurrent networks as models for cortical computation, 3) how the brain could approximate backpropagation, and 4) meta reinforcement learning as a model for rapid learning and theory of mind.

The seminar targets master students, PhD students and senior researchers. If desired, students can acquire credit points.

For further information and updates on the seminar, please enrol on the Moodle course page.

The enrolment key for the course is dlbm1920. If you encounter any problems or require further information, please contact joramkeijser@gmail.com.

We enjoyed preparing this seminar and are looking forward to sharing our excitement with you.

Best wishes,

Joram Keijser, Robert Lange, Denis Alevi & Henning Sprekeler