Introduction to machine learning and python via the HiggsML challenge

I gave a quick tutorial on classification in machine learning during the last IN2P3 school of statistics and I thought it was a good opportunity to introduce python and the ipython notebook on the way for those who were still reluctant to adopt this ecosystem. I used the HiggsML challenge data since the audience was mainly made of particle physicists.

Here are the files for those interested:

Open access explained! #OA

How to write a great research paper

Young PhD students often spend hours reading/watching tons of tutorials about how to write the perfect research paper. Pr. Simon Peyton Jones, from Microsoft Research, gave the kinda talks that provides you with a feeling of satiation that might save you a lot of time. It’s comprehensive, it’s concise, so in principle, you’ll waste less hours on reading and focus more on writing ;).

You can either watch the talk or just look at the slides.

Next LAL student seminar

I’m giving a talk at the next LSD (LAL Student Discussion) on Feb 3 at 10:30. The subject will be on ensemble methods in machine learning and their link to trigger design in particle physics. I’ll try to cover both theoretical foundations of ensemble methods (mainly boosting) and some of most successful algorithms that fit into this framework.

If you’re attending, feel free to post a comment below for feedback/suggestion/remarks. As it is a cross-disciplinary talk, I’d be happy to tackle specific issues related to your daily application of machine learning methods (TMVA etc.).

Prediction with Sequential Models workshop

We’re organizing a workshop at the next ICML in Atlanta titled Prediction with Sequential Models. The topic is vast and one the workshop’s objectives is to gather the different approaches and views together and discuss them. After a very coarse overview  by Gabriel and me, we’ll let the different speakers present their contributions and we’ll conclude with a round table discussing the key points and perspectives. Last but not least, we’ll also have the pleasure to listen to John LangfordHugo Larochelle and Csaba Szepesvári.

Looking forward to it!
If you’re interested in sequential models see you in Atlanta (or leave a comment on G+).

The illustrated guide to a Ph.D, by Matt Might

Last time, I had to explain my young cousins what Ph.D. studies consist of, then, I remembered the subtle depiction of Matt Might in his Illustrated Guide to a Ph.D. It turned out to be very clear for them, so here it is:

Imagine a circle that contains all of human knowledge:

By the time you finish elementary school, you know a little:

By the time you finish high school, you know a bit more:

With a bachelor’s degree, you gain a specialty:

A master’s degree deepens that specialty:

Reading research papers takes you to the edge of human knowledge:

Once you’re at the boundary, you focus:

You push at the boundary for a few years:

Until one day, the boundary gives way:

And, that dent you’ve made is called a Ph.D.:

Of course, the world looks different to you now:

So, don’t forget the bigger picture:


Keep pushing.


I got my PhD at the University of Paris-Saclay in Computer Science and Machine Learning, working under the supervision of Balázs Kégl. My research mainly focused on sequential models for classification, with the motivation of getting accurate classifiers that are fast enough for real-time applications and flexible enough for budgeted learning problems.

I’m particularly interested in supervised learning, reinforcement learning, and how to apply them to different domains*. During my PhD, I was particularly interested in trigger design in High Energy Physics experiments.

Before I delved into the field of research, I followed an engineering curriculum in computer science at the University of Science Houari Boumediene (Algiers) where I graduated in 2009.

*which happens to be named data science now :]


  • C++ and Design Patterns – Graduate / Polytech’ 5ème année
  • Computer Architecture – Undergraduate – second year / Licence Informatique (L2)
  • Web programming – Undergraduate – second year / Licence Informatique (L2)
  • Projet Professionnel – Undergraduate – first year / Licence Informatique (L1)


Contact me

  • Office:   116, Bâtiment 208
  • Mail:   djalel [dot] benbouzid [at] gmail [dot] com
  • Address: Laboratoire de l’Accélérateur Linéaire
    Université Paris Sud 11
    Bâtiment 208
    91898 Orsay cedex
  • Google Maps