You are here:

91261 - Artificial Intelligence in Industry

Academic Year 2020/2021

                
                        Docente:
                        Michele Lombardi
                    
                        Credits:
                        6
                    
                        SSD:
                        ING-INF/05
                    
                        Language:
                        English
                    
                        Teaching Mode:
                        Traditional lectures
                        
                            Campus:
                            Bologna
                        
                            Corso:
                            Second cycle degree programme (LM) in
                            Artificial Intelligence (cod. 9063)

                            Teaching resources on Virtuale

Learning outcomes

At the end of the course, the student has a deep knowledge of industrial applications that benefit from the use of machine learning, optimization and simulation. The student has a domain-specific knowledge of practical use cases discussed in collaboration with industrial experts in a variety of domains such as manufacturing, automotive and multi-media.

Course contents

Brief introduction to Business Analytics

Simplified case studies from industrial domains (in a broad sense) and related solution methods. Representative examples may include:

Anomaly Detection problems
Remaining Useful Life (RUL) prediction
RUL-based maintenance policies in predictive maintenance
Efficient part tracking
Credit class definition
Fair recommendation systems
Power grid management problems
Epidemic control
Production scheduling

General methodologies

Mathematical modeling of an industrial problem
Choosing and evaluating AI techniques for a problem
Approaches for combining and integrating AI methods, such as: encoding, decomposition, subgradient optimization, bilevel optimization, and surrogate models

Seminars and case studies from industrial experts

Readings/Bibliography

The main teaching material will consists of the course slides, which will contain pointers to relevant references.

Teaching methods

Lectures, group discussions, and examples on Jupyter (Python) notebooks

Assessment methods

Individual or group projects, with up to two students per group.

A limited set of topics will be presented in the first half of the course; students will be able to propose their own project topic, which must however be approved by the teacher.

The exam will consist in the presentation and discussion of the project work.

Teaching tools

The course will make extensive use of PDF slides, examples will be given using Jupyter notebooks.

The course will require a number of optimization and Machine Learning software libraries, all free for academic use.

Office hours

See the website of Michele Lombardi