Name: Stephane Chretien
Type: User
Company: Laboratoire ERIC, Université Lyon 2
Bio: Professor at the University of Lyon 2 and researcher at ERIC Lab. My fields of research are Computational Statistics and Machine Learning.
Location: 5 avenue Pierre Mendès France, 69676 Bron
Blog: https://scholar.google.fr/citations?user=T8vcOB4AAAAJ&hl=en
Stephane Chretien's Projects
https://harvard-iacs.github.io/2019-CS109A/
A series of articles to get started into the field of Machine Learning with R language
Introductory tutorial on graphical display of geographical information in R.
Machine learning datasets used in tutorials on MachineLearningMastery.com
A unified framework of perturbation and gradient-based attribution methods for Deep Neural Networks interpretability. DeepExplain also includes support for Shapley Values sampling. (ICLR 2018)
Code corresponding to the paper "Detecting Short-Lasting Topics using Nonnegative Tensor Decomposition".
A minimal and mobile-first blog theme for Jekyll
Deep Learning course in Göttingen April 2018
Graph saliency maps through spectral convolutional networks for brain mapping
A robot powered training repository :robot:
Cours, tutoriels, et exercices pour apprendre le Python et pour découvrir Git & GitHub.
Statistical/Machine learning project with ENSAE and CREST under the supervision of Guillaume Lecué
codes for MOM estimation and outliers detection
Code samples for my book "Neural Networks and Deep Learning"
code for deep learning courses
This code package implements the prototypical part network (ProtoPNet) from the paper "This Looks Like That: Deep Learning for Interpretable Image Recognition"
An implementation of IDS (Interpretable Decision Sets) algorithm.
A game theoretic approach to explain the output of any machine learning model.
Prediction system to predict which user is going to buy a product displayed on a social media advertisement using random forest classification.
Code repo for "A Simple Baseline for Bayesian Uncertainty in Deep Learning"
Contrast-agnostic segmentation of MRI scans
TensorLy: Tensor Learning in Python.
Sampling-based approach to analyse neural networks using TensorFlow
Module for statistical learning, with a particular emphasis on time-dependent modelling