OVERVIEW

The amount of data in industrial applications is exponentially growing. Efficient and sophisticated tools are needed to manage it.
This course presents the most recent methods of data processing and content generation.

AIMS AND CONTENT

LEARNING OUTCOMES

Develop the basic skills for extracting knowledge and knowledge from large data sets, in particular by forming an understanding of the value of data mining in solving real-world problems understanding of foundational concepts underlying data mining understanding of algorithms commonly used in data mining tools ability to apply data mining tools to real-world problems

AIMS AND LEARNING OUTCOMES

At the end of the course, the student

• will have acquired knowledge of AI tools used in the business environment both to build complex predictive models and to generate new content (texts, images, sounds, videos), modeled on the needs of the recipients of the analyses

• will be able to operate at best in the business environment by exploiting a good understanding of the fundamental concepts of Predictive AI and Generative AI

• will be able to tackle a data analysis problem in a group, automatically generate a report, present it and thus understand a business phenomenon.

PREREQUISITES

Coding (Matlab and/or Python and/or R), linear algebra, descriptive and inferential statistics.

TEACHING METHODS

In-class lectures and seminars by external experts.

SYLLABUS/CONTENT

1. Examples of statistical problems and methodologies applied in the business environment
2. Cross-Industry Standard Process for Data Mining (CRISP-DM) for the management of data mining projects
3. Methods for the management of variables for statistical models
4. MultiLayer Perceptron (MLP) and Convolutional Neural Networks (CNN)
5. Introduction to Predictive Maintenance
6. Definition of Predictive AI and Generative AI
7. Predictive AI: from feature engineering to the definition of embedding. Examples of clustering and classification applications in medicine, finance and other sectors
8. Introduction to Recurrent Neural Networks (RNN)
9. History and development of Generative AI
10. Introduction to GANs (Generative Adversarial Networks)
11. The concept of Transformer and (Self-)Attention
12. Applications of Generative AI (texts, images and generative art)

RECOMMENDED READING/BIBLIOGRAPHY

“Deep learning” di Goodfellow, Bengio, Courville. MIT Press Ltd (2016)

“Generative deep learning: teaching machines to paint, write, compose, and play” di Foster. O'Reilly Media (2023)

“Applied survival analysis using R” di Moore. Springer (2016)

“Attention is all you need” di Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser, Polosukhina (2017). In Guyon, Von Luxburg, Bengio, Wallach, Fergus, Vishwanathan and Garnett (eds.). 31st Conference on Neural Information Processing Systems (NIPS). Advances in Neural Information Processing Systems. Vol. 30. Curran Associates, Inc. arXiv:1706.03762.

“Data mining: practical machine learning tools and techniques - 4th Edition” di Witten, Frank, Hall, Pal, Foulds. Kaufmann (2016) 

Scientific papers and online resources for selected applications

TEACHERS AND EXAM BOARD

LESSONS

LESSONS START

According to official academic calendar

Class schedule

The timetable for this course is available here: Portale EasyAcademy

FURTHER INFORMATION

Students who have valid certification of physical or learning disabilities on file with the University and who wish to discuss possible accommodations or other circumstances regarding lectures, coursework and exams, should speak both with the instructor and with Professor Sergio Di Domizio (sergio.didomizio@unige.it), the Department’s disability liaison.