May 28, Tuesday: the first workshop of the consortium
mquet
All scikit-learn consortium partners
are pleased to invite you
to the first annual workshop
Tuesday, May 28, 2019 from 10:00am to 7:00pm
– Welcome coffee from 9:30am –
BNP Paribas Cardif – 8 rue du Port, Nanterre
Access
Sorry, registrations are now closed.
Schedule
[ All presentations in English ]
Welcome address by Stanislas Chevalet, Deputy Chief Executive Officer, Transformation & Development, BNP Paribas Cardif
10.05am: Gaël Varoquaux / Inria
Foreword: the scikit-learn consortium
[See the presentation]
10.20: Roman Yurchak / Inria – Symerio
Tutorial: scikit-learn new features. Preprocessing and imputation methods, estimators for clustering, supervised learning
[Slides from the tutorial and the tutorial notebook]
11.40: Xavier Dupré / Microsoft
ONNX: machine learning model persistence
[See the presentation]
12.00: Jérémie du Boisberranger / Inria
Tutorial: questions of performance in scikit-learn. Parallelism, memory, low-level optimizations
[See the tutorial notebook]
1.00pm: Lunch
2.00: Xavier Renard / AXA
Whitening ML black boxes: where do we stand?
[See the presentation]
2.20: Guillaume Lemaître / Inria
Tutorial: scikit-learn interpretability, linear and tree-based models
[See the tutorial notebook1 and notebook2]
3.40: Peter Entschev / Nvidia
Nvidia Distributed GPU Machine Learning with RAPIDS and Dask
[See the presentation]
4.00: Tung Lam Dang / BNP Paribas Cardif
Scikit-learn: a tool for better model risk governance @ BNPP Cardif
[See the presentation]
4.20: Laurent Duhem / Intel
Speeding up scikit-learn on Intel architectures
[See the presentation]
4.40: Léo Dreyfus-Schmidt & Samuel Ronsin / Dataiku
LeaveNoOneOut: Building a ML platform for everyone
[See the presentation]
5.00: Anton Bossenbroek / BCG
Rapid and collaborative fair data science deployment in strategy consulting
5.20: Olivier Grisel / Inria
Wrap up and perspectives
[See the presentation]
5.30: Round-table discussion: Open source, a model for AI and data science?
6.00: Closing cocktail