Second ML-INFN Hackathon: Starting Level

Europe/Rome
http://cern.ch/go/pk7C (Zoom)

http://cern.ch/go/pk7C

Zoom

Direct link : https://cern.zoom.us/j/63455648268?pwd=T0UrY1VHMGhqK21BSFdXZC8rQ05xUT09 The Meeting ID is 634 5564 8268 with the passcode 11111
Description

 

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

 

Registration is now closed.

You can see the first edition here, with most of the talks attached as video files.

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. Signal / Background discrimination @ LHC: b Tagging AND Higgs Boson Searches
  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:

  • 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: we will add more resources for the hackathon and related projects as soon as they become available,.

Participants
  • Alberto Annovi
  • Alessandro De Falco
  • Alessandro Di Mattia
  • Alessandro Renzi
  • Alessio Fiori
  • Amodio Carleo
  • Andrea Maino
  • Andrea Massironi
  • Annalisa Mastroserio
  • Antonio D'Avanzo
  • Antonio Palasciano
  • Antonio Sidoti
  • Benedetta Camaiani
  • Cristiano Palomba
  • Daniele Massaro
  • Diana Domenichini
  • Elizabeth Long
  • Elvira Rossi
  • Emanuele Leonardi
  • Enrico Catanzani
  • Fabio Colamaria
  • Francesco Cirotto
  • Francesco Faldi
  • Gabriele Martelli
  • Germano Bonomi
  • Giacomo Levrini
  • Gianfranco Paternò
  • Giovanni Di Domenico
  • Giovanni Francesco Tassielli
  • Giuseppe La Vacca
  • Giuseppe Messineo
  • Henrik Munch
  • Ian Postuma
  • Leandro Javier Cieri
  • Leonardo Cristella
  • Lisa Rinaldi
  • LORENZO MACCONE
  • Lorenzo Mirasola
  • Marco Corvo
  • Marco Rocchini
  • Marco Serra
  • Maria Artero Pons
  • Marta Urioni
  • Mateusz Bawaj
  • Matteo Presilla
  • Matteo Tenti
  • Michela Lai
  • Mirko Massi
  • Nicoletta Protti
  • Paolo Mastrandrea
  • Pia Astone
  • Pierluigi Bortignon
  • Pietro Cortese
  • Raffaella Cabini
  • Riccardo Lollini
  • Roberto Franceschini
  • Samrangy Sadhu
  • Samuele Millesoli
  • Sara Rastello
  • Silvia Auricchio
  • Stefano Dusini
  • Tommaso Diotalevi
Surveys
ML_INFN Second Hackathon Survey