32nd Deep Learning Meetup in Vienna

Dear Deep Learners,

We are happy to invite you to the first meetup of 2020! It will happen on January 30th, covering self-supervised learning in different domains, and a report from the NeurIPS 2019 conference.

Talk 1:
Self-Supervised Deep Learning
by Christoph Bonitz, Njinn Technologies

Deep Learning can leverage giant amounts of data, and compute performance has improved a lot. This means that the cost and logistics of creating datasets for supervised learning are often the bottleneck for model performance. In NLP, this limitation has recently been overcome using self-supervised pretraining and supervised fine-tuning. This talk introduces self-supervised and semi-supervised learning in general, and gives a brief tour of some interesting and surprising research in vastly different application areas.

Christoph Bonitz holds a master’s degree in Computational Intelligence, has spent his career in various software engineering and architecture roles building data-centric products, and currently works on a workflow automation platform at Njinn Technologies.

Talk 2:
Report from NeurIPS 2019
by René Donner, contextflow GmbH

The yearly "Neural Information Processing Systems" conference is one of the largest machine learning conferences. In 2019, it took place in Vancouver, from December 8 to 14, with around 13,000 attendees. René will discuss a small selection of the 1,428 papers presented at the conference.

As usual, the meetup will be complemented by hot topics & latest news about Deep Learning, as well as networking.

Looking forward to seeing you at this first meetup of the year 2020,
Jan, Alex, René, Tom