Deep Learning with TensorFlow

IMPORTANT: We will start at 18.00, CE 1 4 Auditoire, EPFL, Lausanne

Five speakers invited from Google, Attention Insight and EPFL extension school presenting tools created for fast and reproducible deployment of deep learning models in TensorFlow, how to create a commercial product using TensorFlow platform and on lessons learned from teaching TensorFlow on online courses.

# SCHEDULE #

18.00 Welcome Note
Pawel Rosikiewicz, Founder at SwissAI

** TensorFlow at Google **

18.05 "TensorFlow 2.0"
Noé LUTZ; Engineering Lead - Brain Applied Zurich - Google AI

18.30 "Reusable Machine Learning with TensorFlow Hub"
Elizabeth KEMP; Software Engineer at Google

18.50 "Learning to Learn"
Quentin DE LAROUSSILHE; Sr Software Engineer, Google Brain; Zürich

19:10 Short break

** TensorFlow Users **

19.15 “Building a Reproducible Machine Learning Pipeline”
Ieva VAIŠNORAITĖ-NAVIKIENĖ; CTO at Attention Insight

19.35 ”TensorFlow - a learner's perspective"
Fred OUWEHAND; Course Developer and Instructor at EPFL Extension School

20.00 Apero

# ABSTRACTS #

Ieva VAIŠNORAITĖ-NAVIKIENĖ
Machine learning is an extremely repetitive process. In case to produce good predictions many steps and even sequences of steps are repeated over and over again. This is particularly important when we are talking about biodata which could be preprocessed in many ways. That adds even more complexity to the data analysis pipeline. Pipeline complexity issue could be tackled in many ways and the Google team suggests many tools that are targeting different aspects of it. In the presentation, I will show Kuberflow - one of the tools to structure containers into pipelines and in that way make the solution more portable and reproducible.

Sponsors: EPFL