3rd CDS pitching day November 28, call for contributions

We are organizing our third CDS pitching day on November 28. Light pitch proposals are due November 7, they should be sent to cdsupsay@gmail.com. The full call is available here: https://docs.google.com/document/d/1XxGXJ6ZWzmkLc8HGbd-ncpojiqopF_x_MICOqQ4e7vE/edit?usp=sharing Consider submitting even preliminary ideas or project proposals if you are a domain scientist looking for data science expertise, especially if you would like to…

Read more

CDS at the Scipy Conference 2018

Members of the CDS and Inria contributed workshops and presentations to SciPy 2018, the 17th annual Scientific Computing with Python conference (July 9-15, 2018). Workshops: Machine Learning with scikit-learn Part 1 & 2 (schedule, materials, video1, video2) Introduction to Geospatial Data Analysis with Python (schedule, materials, video) Pandas .head() to…

Read more

RAMP: IMaging-PsychiAtry Challenge (IMPAC)

A data challenge on Autism Spectrum Disorder detection Autism spectrum disorder (ASD) is a severe psychiatric disorder that affects 1 in 166 children. There is evidence that ASD is reflected in individuals brain networks and anatomy. Yet, it remains unclear how systematic these effects are, and how large is their…

Read more

Internship positions

We are opening two master-level internships at Inria: Neural networks for semantics in databases Learning on spaces endowed by entity similarities in databases Please contact us if you are interested. The internships will be embedded in the Parietal group, under the supervision of Gaël Varoquaux. The timeframe is that of spring…

Read more

NEW single-day RAMP, 12 October: Detecting Mars craters in satellite images

We have opened the registration for the next single-day RAMP on October 12. We will tackle a multi-object filtering problem: detecting Mars craters in satellite images. Please sign up before October 5: https://indico.lal.in2p3.fr/event/4651 The goal of this RAMP is to detect Mars craters in satellite images. Each instance will consist of a small square image patch, embedded…

Read more

New RAMP for classifying pollinating insects

In collaboration with IESF and MNHN Spipoll, we are organizing a third computer vision challenge for classifying pollinating insects. This time we got into the thin tail: we have 70K images and 403 classes, a lot of them with less than 10 examples per class. Pre-registration is open at http://bee-o-diversity-challenge.strikingly.com. This is also the first RAMP with…

Read more

Workshop Galaxy Deblending with Deep Learning

Wednesday, 28 June 2017 from 10:00 to 17:30 at François Arago Centre With the current (DES, KIDs, HSC) and future (LSST, Euclid, WFIRST) generation of large scale deep surveys, we will have to deal with an increasing number of crowded fields in which a high number of objects are blended. This…

Read more

New Postdoc or Research Engineer Position

The selected candidate will be recruited as an employee of the National Museum of Natural History (MNHN-Paris), starting ideally September 2017. PROJECT: Human-machine interaction for identifying insects on photos Since 2010, participants of our citizen science program Spipoll (spipoll.fr) have collected 280,000 pictures of flower-dwellings insects and spiders. This roughly 50k/year…

Read more