Romain WARLOP

Hi, I'm Romain.

I am at data scientist in the french company fifty-five and also a PhD Student in the recommender system field in machine learning with team Sequel at Inria Lille. I also co-manage the association Data for Good which brings together data scientists and non profit organisation to solve their problems through data. 
Learn more about me

Quit smoking

[I liked, I share] Understanding LSTM Networks Recurrent Neural Networks

Humans don’t start their thinking from scratch every second. As you read this essay, you understand each word based on your understanding of previous words. You don’t throw everything away and start thinking from scratch again. Your thoughts have persistence. [By Christopher Olah]
See more ...


Data Scientists For motivated dummies

Discover machine learning techniques applied by data scientist in their everyday life. This article is a little technical.
See more ...

Tennis

Quit smoking

Recommender System How they do it ?

Recommender System is a very active field of machine learning and is applied everywhere : Amazon, Netflix, E-commerce, ... There is many ways to build a recommender system. Discover here a review of the different techniques.
See more ...


Tennis Who will win the match?

Here is a machine learning algorithm design to predict the output of a tennis match. You'll find here all the details of the implementation and visualization of the data and of the output. Maybe a winning bet strategy can be inferred from that ...
Keywords: Features construction - EM algorithm - (Non Linear) Dimensionality reduction
See more ...

Tennis

Quit smoking

[I liked, I share] A Deep Learning Tutorial From Perceptrons to Deep Networks

In recent years, there’s been a resurgence in the field of Artificial Intelligence. It’s spread beyond the academic world with major players like Google, Microsoft, and Facebook creating their own research teams and making some impressive acquisitions. [By IVAN VASILEV on Toptal]
See more ...