Informations

Course beginning:

September  - last week,  2025
Duration 13 weeks.

Lesson timetable

Tuesday

08:00 - 11:00

Room 20, SPV

Wednesday 

08:00 - 10:00

Room 30, SPV

Motivation

Machine Learning is one of the key drivers of modern Artificial Intelligence, enabling systems to automatically extract patterns, adapt to new data, and support decision-making in complex environments.

The motivation for this course is threefold:

• Scientific relevance – ML provides a rigorous framework, grounded in mathematics and statistics, for modeling and understanding data-driven phenomena.
• Technological impact – ML powers today’s most advanced applications, from computer vision and speech recognition to bioinformatics, finance, and autonomous systems.
• Educational value – mastering ML equips students with the conceptual foundations and practical skills required to navigate cutting-edge research and professional innovation.

 

This course is designed to help students bridge theory and practice, preparing them to contribute effectively in both academic and industrial settings.

 

Objectives of the Course

The main goal of the Machine Learning (ML) course is to introduce students to state-of-the-art methods and essential programming tools for the analysis of complex datasets.

The course provides both theoretical foundations and applied perspectives on modern ML techniques, highlighting their statistical underpinnings, practical applicability, and mathematical depth. Students will gain the ability to critically evaluate algorithms, understand their limitations, and apply them in diverse real-world contexts.

The program is structured around four main topics:

1. Mathematical principles underlying modern artificial intelligence.
2. Introduction and review of ML methods, presented with advanced theoretical and mathematical rigor.
3. Specific advanced ML algorithms, studied from both theoretical and practical perspectives.
4. Programming tools and libraries most widely used in ML, with a focus on Scikit-Learn and TensorFlow 2.x.

 

Course syllabus

Part 1: Advanced Mathematics and Statistics, Contextualized for Machine Learning
Part 2: "Classic" ML Algorithms and Their Practical Applications
Part 3: Adaptive Filtering Fundamentals
Part 4: Advanced ML Algorithms
Part 5: Neural Neworks
Part 6: Python
Part 7: Development of a Complete Projects.

 

Each course topic is accompanied by exercises in Python language, and the class and function references of scikit-learn. or TensorFlow

 

References

Textbooks

• Aurelio Uncini, “Introduction to Neural Networks and Deep Learning,” Ed. 2025,  (free pdf available  for the students). 

• Aurelio Uncini, “Mathematical Elements of Modern Artificial Intelligence,” Ed.  2025 (free pdf available  for the students).

• Aurelio Uncini, "Fundamentals of Adaptive Signal Processing," - Springer, ISBN 978-3-319-02806-4, Feb. 2015

Other recommended reading

• Trevor Hastie, Robert Tibshirani, Jerome Friedman, "The Elements of Statistical Learning," Springer 2009.
• Sergios Theodoridis, “Machine Learning: A Bayesian and Optimization Perspective,” 2nd Edition - Elsevier 2020.

Old historical books

• Rumelhart, D.E., Hinton, G.E., & McClelland, J.L. (1986). “A General Framework for Parallel Distributed Processing”, In Rumelhart, D.E., & McClelland, J.L. and the PDP Research Group (1986) Eds. Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Volume 1: Foundations. MIT Press: Cambridge, MA.