First ML-INFN Hackathon

Europe/Rome
Zoom

Zoom

Master Zoom Room for the plenary sessions http://cern.ch/go/pk7C Meeting ID: 634 5564 8268 Passcode: 11111 ... ...
Description

Registration closed; the maximum number of participants has been reached.

We plan to organize a second course after the Summer, stay tuned!

 

New: see proposed groups / use cases on the left menu

 

Welcome to the first edition of the Machine Learning @ INFN (ML_INFN) starting level hackathon, dedicated to INFN Affiliates.

The course is to be considered as "starting level" for Machine Learning topics.The hackathon will be organized over 3 days, distributed as 

  1. General introduction on ML and on its use in INFN (including Clouds)
  2. Tutored hands-on of specific use cases, attempting to reach fully working products; a review of the ML utilization in specific use cases of INFN interest
  3. The hackathon, with participants working in groups trying to achieve a goal in the form of a realistic analyses. In the latter part, presentation of their work is expected and discussed among all the groups.

The use cases for third day ("hackathon")

Upon registration, users will be asked to express a first and second preference for a one of the use cases offered. We will try to

  • whenever possible, satisfy the preference in the order given
  • try to form groups with students with the full range of proficiencies, in order to allow for self-tutoring inside the groups

The list of available use cases for the hackathon are currently (there could be additions depending on the registration process and on the status of other opportunities):

  1. discrimination of hadronic jets from light and heavy flavours @ LHC
  2. autoencoders for VIRGO GW signal analysis
  3. classification of lesions in medical physics 

 

Prerequisites

Technical: access to INFN Cloud provided resources

NOTE: users will use INFN-Cloud resources and this does not require any specific INFN-Cloud authorization. 

Please read and comply with the recommendations in the side menu "technical prerequisite".

Machine learning related knowledge

The hackathon is to be considered as entry level for Machine Learning. Still, some fluency in the tools to be used is a prerequisite and it is needed to speed up the tutoring. In particular, we expect:

  • some fluency in Python:
    • basic program flow, definition and use of variables
    • definition and utilization of functions
    • package management (import, install via pip)
  • some fluency in numpy:
    • arrays, basic operations, reshaping
  • some fluency on matplotlib:
    • how to define and plot a basic figure
  • some fluency on online python notebooks
    • (like SWAN, Jupyter, Google Colab)

In case you do not feel proficient enough in the previous items, we suggest a list of entry level tutorial / documentation we advise to read and test before the Hackathon, in order to be able to follow with profit the presentations and the hands-on. This can be found in the side menu, at the entry "Pre-tutorial Self-teaching".

Registration

Attending the hackathon is free and happens via the entry in the side menu.

The number of participants can be limited, depending on the tutoring and technical capabilities.

Upon registration, we will require info like

  • INFN Affiliation
  • Research interests
  • Proficiency level in Machine Learning and related tools
  • Specific interests in Machine learning  techniques
  • The preferred use case for the third day (first and second choice)

Additional Material

Please consider visiting again this page from time to time; as soon as available, we will add more resources for the hackathon and related projects.

Participants
  • Alessandro Bertolin
  • Alessio Scagliola
  • Alexei Sytov
  • Andrea Giachero
  • Andrea Virtuoso
  • Antonio Gilardi
  • Antonio Iuliano
  • Anushree Ghosh
  • Bianca Sofia Pinolini
  • Calum Milloy
  • Costantino Pacilio
  • Davide Cicolari
  • Davide Marcato
  • Federica Giacchino
  • Filippo Santoliquido
  • Flavia Cetorelli
  • Francesca Brero
  • Francesco Puosi
  • Gianfranco Vecchio
  • Giorgio Del Castello
  • Giovanni Arena
  • Giovanni Costantini
  • Giovanni Guerrieri
  • Giulia Colelli
  • Giuliano Iorio
  • Guglielmo Costa
  • Isabella Oceano
  • Jacopo Pinzino
  • Jacopo Soldateschi
  • Leandro Javier Cieri
  • Leonardo Barzaghi
  • Leonardo Vannoli
  • Lorenzo Domenichetti
  • Lorenzo Neri
  • Luca Giommi
  • Luca Morselli
  • Marco Dall'Amico
  • Marco Di Luzio
  • Marco Fazzi
  • Massimo Nocente
  • Mauro Emanuele Dinardo
  • Michela Lai
  • Michele Barsanti
  • Odysse Halim
  • Oleh Fedkevych
  • Ornella Juliana Piccinni
  • Piergiorgio Antonini
  • Simone Capelli
  • Simone Gennai
  • Simone Stracka
  • Stefano Gariazzo
  • Stefano Torniamenti
  • Valentina Diolaiti
  • Valentina Sola
Surveys
Hackathon Feedback Form