RAMPS

Rapid Analytics and Model Prototyping

The RAMP is a versatile management and software tool for connecting at the University of Paris-Saclay data science to domain sciences, which is the main mission of the CDS.

Similarly to a data challenge, the data provider arrives with a prediction problem and a corresponding data set. An experienced data scientist then cleans and curates the data, formalises the problem and sets up the problem using the RAMP software. When the data science problem requires the mastering of a specific tool, the RAMP event can be preceded by a Training Sprint. Part of the Training Sprint can also be devoted to introducing the domain science problem, otherwise this introduction takes place at the beginning of the RAMP.

The following RAMPS have been organised:

HiggsML

The HiggsML RAMP was the first event of a series of bootcamps that the CDS was launching. This first session was about a gentle introduction to practical machine learning through a concrete application to the Higgs-ML challenge data (ATLAS experiment).

The event took place at Proto204 in january 2015 and we had a special guest, Gábor Melis, who recently won the Higgs-ML competition held by Kaggle.com.

Health care

The Health care RAMP took place on February 2015 at PROTO204 and it was the second edition of the CDS bootcamps in Machine Learning and Data Science.

Classifying variable stars

The Classification of variable stars RAMP took place at Proto204 on April 2015 and was on Astrophysics, more precisely, on classification of variable stars from their light curves (luminosity vs time profiles).

El Niño prediction

Similarly to the variable stars RAMP, in El Niño Prediction RAMP the pipeline consisted of a feature extractor and a predictor.  This RAMP took place at PROTO204 on June 2015, and its objective was to predict six months ahead the temperature at surface (TAS) in the El Niño 3.4 region from TAS data simulated by the CCSM4 model.

Pollenating insects

The Pollenating Insects RAMP took place at PROTO204 on October 2015.

In this RAMP we classified images of pollenating insects from the SPIPOLL crowdsourcing project of the Paris Museum of Natural History (MNHN). The RAMP is brought to you by Romain Julliard (MNHN) and your regular coaches. We are grateful to the Université de Champagne-Ardenne ROMEO HPC Center and NVIDIA for providing the GPU backend and engineering support for the RAMP, and to Proto204 for hosting the event.

Macroeconomic surrogate

In the Macroeconomic Surrogate RAMP  we learnt a surrogate model for an agent-based macroeconomic model (ABM) and an objective function. The goal was to have a fast filtering algorithm that can replace this slower simulation in, for example, a stochastic optimization or approximate Bayesian computation.

The event took place on February 2016 at the Maison des Sciences Économiques.

HEP detector anomalies

The purpose of the LHC Atlas RAMP was to detect anomalies in the LHC Atlas detector,  to Separate a skewed data point from a original data point.

The event took place on May 2016 at the Auditorium Pierre Lehmann (LAL).

Drug classification for Spectra

Chemotherapy is one of the most used treatment against cancer.  To prevent wrong medication, some recent French regulations impose the verification of anti-cancer drugs before their administration. In this context, the goal of the Drug Classification RAMP was to develop prediction models able to identify and quantify chemotherapeutic agents from their Raman spectra.

The event took place on May 2016 at PROTO204.

 

 

 

 

 

 

Comments are closed