Fifth ML-INFN Hackathon: Advanced Level

Europe/Rome
Building C (INFN Pisa)

Building C

INFN Pisa

Largo Bruno Pontecorvo 3
Francesca Lizzi (Istituto Nazionale di Fisica Nucleare), Lucio Anderlini (Istituto Nazionale di Fisica Nucleare)
Description
undefined

Welcome to the Fifth edition of the Machine Learning @ INFN (ML_INFN) advanced level hackathon, dedicated to INFN affiliates.  This edition is hosted at INFN Sezione di Pisa.

Notably, it is the second Hackathon to happen in Person, so please apply only if you are planning to come to Pisa. The logistics allow for ~ 20 participants.

You may want to check the indico pages of the first (entry level), second (entry level), third (advanced level), and fourth (entry level) editions, with most of the talks attached as video files.

The mandatory registration process will be open from Monday October 16th to Monday October 23th. 

In case of a number of registrations exceeding the available positions, the applications will be ranked and selected on the basis of the scientific CV of the applicants.

The successful applicant will be informed by November 1st. Please do not book hotel/flight before a positive confirmation.

The course is to be considered as "advanced level" for Machine Learning topics. The hackathon will be organized over 4 days, distributed as 

  1. Infrastructure and tools for Machine Learning at INFN
  2. Models constitued of multiple neural networks
  3. Models for data beyond tabular format
  4. Ongoing developments towards the future of Machine Learning

 The afternoons of days 2 and 3 will be devoted to experimenting the various methods and architectures with the help of tutors.

Upon registration, users will be asked to express their preferences 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. Transformers and Visual Transformers
  2. U-Net and medical image segmentation
  3. Solving partial differential equation with deep learning
  4. Anomaly detection with Autoencoders in CMS Data Quality Monitoring

 

 

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 advanced level for Machine Learning. Hence, students are expected to have a starting level of understanding of machine learning and on the technologies it implies. For example

  • good fluency in Python:
    • program flow, definition and use of variables
    • definition and utilization of functions
    • package management (import, install via pip)
  • fluency in numpy:
    • arrays, basic operations, reshaping
  • fluency on matplotlib:
    • how to define and plot a basic figure
  • fluency on online python notebooks
    • (like SWAN, Jupyter, Google Colab)
  • basic concepts of Deep Learning
    • (e.g.) working principle of dense and convolutional layers 
    • epochs, batches, optimizers, metrics...

Registration

Attending the hackathon is free but the registration is mandatory (see 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 second and the third day (first and second choice)

Sponsors and support to the event

The event is sponsored by the Pisa unit of the Italian Institute for Nuclear Physics (INFN), by the Artificial Intelligence in Medicine:next steps INFN initiative, by the Medipix collaboration, by the Future Artificial Intelligence Research (FAIR) initiative and by the Italian Research Center on High Performance Computing, Big Data and Quantum Computing (ICSC Foundation).

 

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
  • Agnese Robustelli Test
  • Andrea Paccagnella
  • Angelo Raimondi
  • Antonio Corvino
  • Antonio D'Avanzo
  • Cornelia Arcaro
  • Davide Miceli
  • Domingo Ranieri
  • Edoardo Leandri
  • Fernando Garcia-Avello Bofias
  • Francesco Artuso
  • Francesco Tarantelli
  • Francesco Tenchini
  • Gaia Bartoli
  • Giuseppe Di Somma
  • Laura Pintucci
  • Manuel Naviglio
  • Mattia Romeo
  • Michele Vacatello
  • Patrick Asenov
  • Roberto Benocci
  • Rosa Petrini
  • Sara Saponaro
  • simon kanka
  • Tommaso Diotalevi
Surveys
Survey on the Fifth Edition of the ML-INFN Hackathon
    • Cloud Infrastructure for Interactive Analysis and Machine Learning: Monday Sala Riunioni 250

      Sala Riunioni 250

      INFN Pisa

      Largo Bruno Pontecorvo 3
      • 1
        Welcome and introduction
        Speakers: Francesca Lizzi (Istituto Nazionale di Fisica Nucleare), Lucio Anderlini (Istituto Nazionale di Fisica Nucleare)
      • 2
        INFN Pisa Computing Centre
        Speaker: Enrico Mazzoni (Istituto Nazionale di Fisica Nucleare)
      • 3
        Infrastructure, Platform and Software as Services in INFN Cloud
        Speaker: Luca Giommi (Istituto Nazionale di Fisica Nucleare)
      • 4
        A scientific perspective on Cloud scalability
        Speakers: Daniele Spiga (Istituto Nazionale di Fisica Nucleare), Diego Ciangottini (INFN Perugia)
      • 4:00 PM
        Coffee break
      • 5
        Containerizing ML applications for development, training and deployment
        Speaker: Lucio Anderlini (Istituto Nazionale di Fisica Nucleare)
      • 6
        Hands-on ML_INFN instances, with Jupyter and beyond
        Speaker: Lucio Anderlini (Istituto Nazionale di Fisica Nucleare)
    • Advanced Machine Learning Lectures Sala Riunioni 250

      Sala Riunioni 250

      INFN Pisa

      Largo Bruno Pontecorvo 3
    • 1:00 PM
      Lunch Break Building C

      Building C

      INFN Pisa

      Largo Bruno Pontecorvo 3
    • Hackathon exercises: Tuesday Building C

      Building C

      INFN Pisa

      Largo Bruno Pontecorvo 3
      • 10
        Hackathon: Anomaly detection with Autoencoders in CMS Data Quality Monitoring Sala Riunioni 133

        Sala Riunioni 133

        INFN Pisa

        Speakers: Alkis Papanastassiou, Benedetta Camaiani (Istituto Nazionale di Fisica Nucleare)
      • 11
        Hackathon: Transformers and Visual Transformer Sala Riunioni 250

        Sala Riunioni 250

        INFN Pisa

        Speakers: Stefano Giagu (Istituto Nazionale di Fisica Nucleare), Francesco Vaselli (Istituto Nazionale di Fisica Nucleare)
      • 12
        Coffee break Building C

        Building C

        INFN Pisa

        Largo Bruno Pontecorvo 3
      • 13
        Hackathon: Anomaly detection with Autoencoders in CMS Data Quality Monitoring Sala Riunioni 133

        Sala Riunioni 133

        INFN Pisa

        Speakers: Alkis Papanastassiou, Benedetta Camaiani (Istituto Nazionale di Fisica Nucleare)
      • 14
        Hackathon: Transformers and Visual Transformer Sala Riunioni 250

        Sala Riunioni 250

        INFN Pisa

        Speakers: Francesco Vaselli (Istituto Nazionale di Fisica Nucleare), Stefano Giagu (Istituto Nazionale di Fisica Nucleare)
    • Advanced Machine Learning Lectures Sala Riunioni 250

      Sala Riunioni 250

      INFN Pisa

      • 15
        Introduction to solving differential equations with machine learning
        Speakers: Alessandro Bombini (Istituto Nazionale di Fisica Nucleare), Lucio Anderlini (Istituto Nazionale di Fisica Nucleare)
      • 10:40 AM
        Coffee break
      • 16
        Introduction to CNN, Autoencoders and U-Net
        Speaker: Francesca Lizzi (Istituto Nazionale di Fisica Nucleare)
      • 17
        Hands-on generative models
        Speakers: Francesco Vaselli (Istituto Nazionale di Fisica Nucleare), Matteo Barbetti (INFN Firenze), Simone Capelli (Istituto Nazionale di Fisica Nucleare)
    • 1:00 PM
      Lunch break Building C

      Building C

      INFN Pisa

      Largo Bruno Pontecorvo 3
    • Hackathon exercises: Wednesday Building C

      Building C

      INFN Pisa

      Largo Bruno Pontecorvo 3
      • 18
        Hackathon: Lung Sementation on Chest X-Ray images with U-Net Sala Riunioni 133

        Sala Riunioni 133

        INFN Pisa

        Speakers: Ian Postuma (Istituto Nazionale di Fisica Nucleare), Mr Arman Zafaranchi (UniPi), Dr Lorenzo Marini (Istituto Nazionale di Fisica Nucleare)
      • 19
        Hackathon: Solving differential equation with deep learning Sala Riunioni 250

        Sala Riunioni 250

        INFN Pisa

        Speakers: Alessandro Bombini (Istituto Nazionale di Fisica Nucleare), Lucio Anderlini (Istituto Nazionale di Fisica Nucleare)
      • 4:00 PM
        Coffee break Building C (INFN Pisa)

        Building C

        INFN Pisa

        Largo Bruno Pontecorvo 3
      • 20
        Hackathon: Lung Sementation on Chest X-Ray images with U-Net Sala Riunioni 133

        Sala Riunioni 133

        INFN Pisa

        Speakers: Arman Zafaranchi (UniPi), Ian Postuma (Istituto Nazionale di Fisica Nucleare), Dr Lorenzo Marini (Istituto Nazionale di Fisica Nucleare)
      • 21
        Hackathon: Solving differential equation with deep learning Sala Riunioni 250

        Sala Riunioni 250

        INFN Pisa

        Speaker: Alessandro Bombini (Istituto Nazionale di Fisica Nucleare)
    • 22
      Social dinner Alla Maniera di Grace

      Alla Maniera di Grace

    • Ongoing developments and future scenarios Sala Riunioni 250

      Sala Riunioni 250

      INFN Pisa

      • 23
        AI in streaming readout data acquisition and real-time inference
        Speaker: Marco Battaglieri (Istituto Nazionale di Fisica Nucleare)
      • 24
        Hands-on: streaming readout
        Speaker: Fabio Rossi
      • 25
        An overview of Machine Learning in Medicine and Medical Physics
        Speaker: Alessandra Retico (Istituto Nazionale di Fisica Nucleare)
      • 10:40 AM
        Coffee break
      • 26
        An overview of Machine Learning applications in HEP
        Speakers: Andrea Rizzi (INFN Pisa), Andrea Rizzi (Istituto Nazionale di Fisica Nucleare)
      • 27
        Quantum Machine Learning and its applications to HEP
        Speaker: Lorenzo Sestini (Istituto Nazionale di Fisica Nucleare)
      • 28
        Final remarks and closing
        Speakers: Francesca Lizzi (Istituto Nazionale di Fisica Nucleare), Lucio Anderlini (Istituto Nazionale di Fisica Nucleare)