MLCourse-INFN-2022

• The course will take place on November 7-11 2022, 10:00 - 12:00 and 14:00 - 16:00
• Course schedule here
• This repository contains material (notebooks and slides) for the INFN CCR Course 'Big Data and ML'

Pre-requisites

• Basic knowledge of python

Practicalities

• This is an online course.
  • We will use zoom
  • Please try it before the course starts, so that you're setup.
• Every day we will have a mixture of theoretical and hands-on sessions.

Hands-on session

• please read this first
• point your browser to the link we provided you. It looks something like https://jhub.some.ip.address.myip.cloud.infn.it/
• on the first day, open a terminal and clone this repository:

git clone https://github.com/Course-bigDataAndML/MLCourse-INFN-2022.git

• The Jupyter notebook documentation can be found here

Before the course starts

• We will be using python, in particular I advise you to get familiar with Jupyter notebooks, numpy and pandas before the course starts. No expert knowledge is required, but doing a couple of tutorials on these topics (easily found on the web) is highly recommended.
• The hands-on will be done on the INFN cloud. Please follow the instructions below and let us know if you have issues.

Access to INFN Cloud

• if you are already an INFN cloud user, let us know. We need to add you to the resource group for this course
• if you never used INFN cloud, you need to register:
  • Please follow these steps.
  • in the notes, specify that you're asking for access to participate in the Big Data and ML course

Access to JupyterHub

• You will receive by email a link to your Jhub. The url looks something like https://jhub.some.ip.address.myip.cloud.infn.it/
  • Click on the link, and accept any security exceptions you might get
  • you will need to authenticate with IAM
  • you will get to a page that says “Authentication required for …”, click on “Authorize”
  • When you get to the server creation page, chooose the option: “Large - 4CPU 8GB”
  • It might take a few minutes for the server to start
  • in case you get timeout errors, and server creation fails, simply reload the link and try againL

Schedule

Lunedi 7 novembre

10:00 - 12:00 Introduction to Big Data concepts (Legger)

14:00 - 15:00 Distributed Computing for big Data and ML I (Vallero)

15:00 - 16:00 Esercitazioni (Legger, Vallero, Antonacci)

Martedi 8 novembre

10:00 - 12:00 Introduction to Machine Learning (Legger)

14:00 - 15:00 Distributed Computing for big Data and ML II (Vallero)

15:00 - 16:00 Esercitazioni (Legger, Vallero, Antonacci)

Mercoledi 9 novembre

10:00 - 12:00 Introduction to Deep Learning and Neural Networks (Legger)

14:00 - 15:00 Distributed Computing for big Data and ML III (Vallero)

15:00 - 16:00 Esercitazioni (Legger, Vallero, Antonacci)

Giovedi 10 novembre

10:00 - 12:00 Deep Learning architectures: CNN, Autoencoders, RNN (Diacono)

14:00 - 16:00 Esercitazioni (Diacono)

Venerdi 11 novembre

10:00 - 11:00 Introduction to INFN Cloud (Donvito)

11:00 - 12:00 Introduction to INFN Cloud services (Antonacci)

14:00 - 16:00 Esercitazioni e prova d’esame (Legger, Vallero, Antonacci)