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.
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
The student will be able manage a data analysis problem in a group, generate a report and thus understand a business phenomenon.
Coding (Matlab/Python/R), linear algebra, probability and statistics, Machine Learning
In-class lectures and laboratory sessions with exercises in Matlab/Python/R
1 Introduction to data science in the business framework 2 Classic machine learning methods for classification and regression problems 3 Data-centric approaches to improve real-world datasets 4 Methods of optimal selection of the features 5 Neural networks and deep learning 6 Convolutional Networks (CNN) 7 Applications to computer vision 8 Definition of Predictive AI and Generative AI 9 Predictive AI: from feature engineering to the definition of Embedding. Projection into the space of embeddings, clustering and classification algorithms 10 Introduction to Recurrent Neural Networks (RNN) 11 History and development of Generative AI 12 Introduction to GANs (Generative Adversarial Networks) 13 The concept of Transformer and (Self-)Attention 14 Applications of Generative AI 15 Creative text generation 16 Image generation and generative art 17 Applications in medicine, finance, and other industries
"Deep Learning" by Ian Goodfellow, Yoshua Bengio, Aaron Courville. "Generative Deep Learning" by David Foster. "Probabilistic Machine Learning" by K,P.Murphy (Volume 1) "An Introduction to Statistical Learning with Applications in Python", by G.James et al. Scientific papers and online resources for selected applications
FRANCESCO PORRO (President)
FABRIZIO MALFANTI
EVA RICCOMAGNO (Substitute)
SARA SOMMARIVA (Substitute)
According to official academic calendar
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.
