- 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)
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