Risorse bibliografiche
Risorsa bibliografica obbligatoria
Risorsa bibliografica facoltativa
Scheda Riassuntiva
Anno Accademico 2019/2020
Tipo incarico Dottorato
Docente Boracchi Giacomo
Cfu 5.00 Tipo insegnamento Monodisciplinare

Corso di Dottorato Da (compreso) A (escluso) Insegnamento

Programma dettagliato e risultati di apprendimento attesi

VERY IMPORTANT: This is a residential course to be held in Lecco Campus of Politecnico di Milano. It will take 4 consecutive days and all the registered students will be provided with meals. Up to 20 students can be freely hosted in shared double rooms of the student dormitory of the Lecco campus. 

A limited number of students can be enrolled and registration will close earlier than other courses. Prerequisite applies to all the participants. Read the course notes for details concerning the enrollment procedures.


Overview: Deep learning models have proven to be very successful in multiple fields in science and engineering, ranging from autonomous driving to human machine interaction. Deep networks and data-driven models have often outperformed traditional hand-crafted algorithms and achieved super-human performance in solving many complex tasks, such as image recognition.

The vast majority of these methods, however, are still meant for numerical input data represented as vectors or matrices, like images. More recently, the deep-learning paradigm has been successfully extended to cover non-matrix data, which are challenging due to their sparse and scattered nature (e.g., point clouds or 3D meshes) or presence of relational information (e.g., graphs). Neural-based architectures have been proposed to process input data such as graphs and point clouds: such extensions were not straightforward, and indicate one of the most interesting research directions in computer vision and pattern recognition.


Mission and goal: This course aims at presenting data-driven methods for handling non-matrix data, i.e., data that are not represented as arrays. The course will give an overview of machine learning and deep learning models for handling graphs, point clouds, texts and data in bioinformatics. Moreover, most relevant approaches in reinforcement learning and self-supervised learning will be presented.


Topics: Lectures, delivered in English, provide an overview of recent solutions for adopting data-driven (and deep learning) models in the following domains:

  • graph mining
  • 3D shape analysis and registration 
  • text mining 
  • bioinformatics 

Moreover, the following fundamental learning problems in machine learning will be addressed:

  • reinforcement learning  
  • inferring causality
  • self-supervised learning 


Course Organization: This is a residential course to be held in the Lecco campus of Politecnico di Milano. The course is organized in 6 lecture slots (4 hour each) given by an invited professor/researcher in a tutorial-style. Moreover, all participants are invited to present their research activities – preferably but not necessarily related to the course topics – in a poster session to be held after the lectures. Two poster sessions in the evening have been scheduled. These will be excellent opportunities to discuss with speakers, organizers and buddies about each other research activities.


Prerequisites: This is not an introductory course. This is instead an advanced course and all the perspective participants have to fulfil the following pre-requisites:

  • Having a solid background in machine learning, neural networks, linear algebra and optimization.
  • Being familiar with deep learning. Topics like CNN, LSTM won’t be covered and constitute a prerequisite.

Note Sulla Modalità di valutazione

Final assessment will be based on participation at classes/poster sessions and/or on a final discussion. Projects are available only upon requests, but required for MSc students.

Intervallo di svolgimento dell'attività didattica
Data inizio
Data termine

Calendario testuale dell'attività didattica
The course will be entirely held online, in a MS Teams meeting Click here to register

Lectures will be held in tutorial-like sessions by invited speakers. The course organizers (Giacomo Boracchi, Cesare Alippi, Matteo Matteucci) will be chairing these sessions.
Lecture schedule follows:

  • Tuesday June 23rd 2020, 14:30 - 18:30 Alessandro Giusti Senior Researcher at IDSIA, Lugano
    Title: Self-supervised Learning and Domain Adaptation
  • Wednesday June 24th 2020, 9:00 - 13:00 Alessandro Lazaric Facebook Paris
    Title: Reinforcement Learning And Application Of Deep-learning Models In RL
  • Wednesday June 24th 2020, 14:30 - 18:30 Mark Carman Politecnico di Milano
    Title: Deep Learning Models For Text Mining And Analysis
  • Thursday June 25th 2020, 9:00 - 13:00 Jonathan Masci NNAISENSE SA, Switzerland
    Title: Machine Learning And Deep Learning Models For Handling Graphs
  • Thursday June 25th 2020, 14:30 - 18:30 Maks Ovsjanikov Laboratoire d'Informatique (LIX), École Polytechnique, France
    Title: 3d Shape Matching and Registration
  • Friday June 26th 2020, 9:00 - 13:00 Gianluca Bontempi Universitè Libre de Bruxelles, Belgiu
    Title: Machine Learning To Infer Causality And Its Application In Bioinformatics

  • Bibliografia

    Mix Forme Didattiche
    Tipo Forma Didattica Ore didattiche
    laboratorio informatico
    laboratorio sperimentale
    laboratorio di progetto

    Informazioni in lingua inglese a supporto dell'internazionalizzazione
    Insegnamento erogato in lingua Inglese

    Note Docente

    The course will be held online. Click here to register

    Invited Speakers: - Alessandro Giusti (Senior Researcher at IDSIA, Lugano) - Alessandro Lazaric (Facebook Paris) - Mark Carman (Politecnico di Milano) - Jonathan Masci (NNAISENSE SA, Switzerland) - Maks Ovsjanikov (Laboratoire d'Informatique (LIX), École Polytechnique, France) - Gianluca Bontempi (Universitè Libre de Bruxelles, Belgium) Course Organizers and Lectures Chairing - Giacomo Boracchi (Politecnico di Milano) - Cesare Alippi (Politecnico di Milano) - Matteo Matteucci (Politecnico di Milano)
    schedaincarico v. 1.6.5 / 1.6.5
    Area Servizi ICT