Advanced Topics in Machine Learning and Optimization

General information

Degree: Master of Science in Artificial Intelligence Systems
Period: September - December

Objectives

The course aims at introducing students to some selected advanced topics on machine learning and optimization. The topics are chosen so as to cover relevant recent research directions and challenges for the machine learning and artificial intelligence community, as well as promising technological advancements.

Prerequisites

A good knowledge of the basics of machine learning (including deep learning) and artificial intelligence (including logic and probabilistic reasoning) is essential. Students are expected to take this course after completing Machine Learning and Fundamentals of Artificial Intelligence from the first year of the AIS degree (or similar teachings).

Content

A preliminary list of topics that will be covered throughout the course is provided below:

  • Explainable Artificial Intelligence
  • Statistical Relational Artificial Intelligence
  • Neuro-Symbolic integration
  • Graph Neural Networks
  • Structured-output learning
  • Auto-ML
  • Active learning
  • Reinforcement learning
  • Quantum machine learning

Course Information

Instructors: Andrea Passerini
Email:
Stefano Teso
Email: stefano.teso@unitn.it
Office hours: Arrange by email
Lecture time: Wednedsay 15:30-17:30 (room a107)
Thursday 9:30-11:30 (room a109)
Communications: Please check the moodle page of the course for news and updates.
Bibliography: Each topic will be presented with slides accompanied by a list of relevant scientific publications to be used as reference material.
Slides: Graph Neural Networks [slides] [handouts] [notebook]
Structured Output Prediction [slides] [pystruct notebook] [pytorch-transformers notebook]
Statistical Relational AI [slides] [handouts] [notebook]
Neuro-Symbolic Integration [slides] [handouts] [notebook]
Explainable Machine Learning [slides]
Gray-box Models [slides]
Active Learning [slides]
AutoML Seminar [slides]
Quantum Machine Learning Seminar [slides]
Program Synthesis Seminar [slides]

Exams

Modality: The student will be asked to realize a project concerning one or more of the topics seen during the course and write a short report. The exam will consist of the evaluation of the project (50%) and the discussion of the report and the topics behind it (50%).
Projects: The list of available projects can be found here. Check the current assignment status here to find projects that are still available. Feel free to write the contact person of each project for further information. Once you decided about a project, inform the contact person to have the project assigned to you. Write andrea.passerini@unitn.it for requests about custom projects.