[DMANET] WOLVERINE 2021: ?Workshop on Open Problems in Learning and Verification of Neural Networks

Dear Colleagues,

We are excited to invite you to the highly interactive virtual WOLVERINE 2021: "Workshop on Open Problems in Learning and Verification of Neural Networks", which will be held on Monday, October 18, during ATVA 2021.

The goal of WOLVERINE is to foster networking and active discussions with a hope to spark new interdisciplinary collaborations. WOLVERINE welcomes researchers in formal methods, machine learning, and their intersection.

Workshop Schedule:

First hour: keynote talk. given by Prof. Sheila McIlraith.
Second hour: short invited talks. We will host 5 short invited talks (10-15min each). Each speaker will present their area of expertise in the intersection between formal methods and AI.
Third hour: round tables. Each speaker from the previous session will host a (virtual) table and moderate a discussion on the topic of his/her choice: we will discuss the challenges and open problems in the field and discuss novel approaches to tackle these challenges.
Fourth hour: poster session. Participants are invited to present their work (published or ongoing) in a poster session on Gather.town.

We have a terrific line-up of invited speakers:

Sheila McIlraith (University of Toronto, Canada): Keynote speaker.

Ofra Amir (Technion, Israel): Explainable Artificial Intelligence.
Guy Katz (Hebrew University, Israel): Robustness.
Markus Rabe (Google): Neurosymbolic Methods.
Matthijs Spaan (TU Delft, The Netherlands): Safe Reinforcement Learning.
Aws Albarghouthi (University of Wisconsin–Madison, USA): Fair Machine Learning.

More details:
https://wolverine2021.github.io

Registration costs: free of charge!

Registration:
https://formal-analysis.com/atva/2021/workshop.html

Looking forward to seeing you on October 18!

Kind regards,
WOLVERINE Team
Anna Lukina, Guy Avni, Mirco Giacobbe, Christian Schilling

**********************************************************
*
* Contributions to be spread via DMANET are submitted to
*
* DMANET@zpr.uni-koeln.de
*
* Replies to a message carried on DMANET should NOT be
* addressed to DMANET but to the original sender. The
* original sender, however, is invited to prepare an
* update of the replies received and to communicate it
* via DMANET.
*
* DISCRETE MATHEMATICS AND ALGORITHMS NETWORK (DMANET)
* http://www.zaik.uni-koeln.de/AFS/publications/dmanet/
*
**********************************************************