Kipoi - Seminar

The monthly virtual seminar series is designed as a platform for interested Kipoi users and developers and will host talks on the applications of deep learning on biological data. The seminar is held on every first Wednesday of the month at 5:30 p.m. - 6:30 p.m. CET. We are also happy to share the recordings of the seminar on YouTube.

How to take part

The Virtual Seminar Series takes place via Zoom. To take part in the seminar, you can register for the online Zoom conference here. Your personal join link will be valid for all upcoming lectures of the series.

How to apply as a speaker

The seminar is a great opportunity to present your recent work to a large international audience. If you want to apply as a speaker, please use the contact in the registration confirmation email.

Next seminar

Title: GFlowNets for Scientific Discovery
1 June 2022 5:30 p.m. - 6:30 p.m. Central European Time

Speaker: Yoshua Bengio, Université de Montréal, Mila – Quebec Artificial Intelligence Institute

Abstract:

When the space of explanations or the space of candidate solutions (e.g. drugs, gene regulatory network) is exponentially large, how can an AI-based system efficiently explore it and make causal sense of the underlying unknown reality? I will introduce a new machine learning framework related to variational inference called generative flow networks or GFlowNets which may be a key deep learning-based ingredient towards answering such questions, guided by inspiration of how humans go at it. How can we model distributions about hypotheses that are not vectors but complex structured objects like graphs or equations? How can we use these to estimate epistemic uncertainty and guide knowledge acquisition through experimental design?

Upcoming speakers

  • 1 June 2022 - Yoshua Bengio, Université de Montréal, Mila – Quebec Artificial Intelligence Institute

Previous speakers

The scientific committee