Wednesday, December 13, 2017

Ce soir Paris Machine Learning Meetup #4 Season 5: K2, Datathon ICU, Scikit-Learn, Multimedia fusion, Private Machine Learning

So today is Paris Machine Learning Meetup #4, Season 5. Wow ! Thanks to Invivoo for sponsoring this meetup (food and drinks afterwards) and especially thanks for give us this awesome place!

The video streaming is here:

Capacity := +/- 170 seats / First-come-first-serve / then doors close

Schedule :

6:45PM doors open / 7-9:00PM talks / 9-10:00PM drinks/foods / 10:00PM end

Gael Varoquaux (INRIA), Some new and cool things in Scikit-Learn

An update on the scikit-learn project: new and ongoing features, code improvements, and ecosystem.

Nhi Tran (Invivoo), Multimedia fusion for information retrieval and classification

“Multimodal information fusion is a core part of various real-world multimedia applications. Image and text are two of the major modalities that are being fused and have been receiving special attention from the multimedia community. This talk focuses on the joint modelling of image and text by learning a common representation space for these two modalities. Such a joint space can be used to address the image/text retrieval and classification applications.”

Morten Dahl, Private Machine Learning

By mixing machine learning with cryptographic tools such as homomorphic encryption we may hope to for instance train model on sensitive data previously out of reach. Although still maturing, in this talk we will look at some of these techniques and how they were applied to a few concrete use cases.

Hardware: The War for AI supremacy, Recent developments, a short reviewIgor Carron,

This is a small review of the recent hardware development in Machine Learning/Deep Learning.

No comments: