Machine Learning

Period: First Semester

Course units contents: Motivation; components of the learning problem and applications of Machine Learning. Supervised and unsupervised learning.

1. Introduction to Supervised Learning: Data, Classes of models, Losses, probabilistic models and assumptions on the data. Regression and Classification.

2. Model complexity, bias variance tradeoff and generalization. Validation and Model Selection, Cross Validation.

3. Models for Regression: Linear Regression, regularization.

4. Simple Models for Classification: Logistic Regression, Perceptron, Naïve Bayes Classifier.

5. Kernel Methods: Support Vector Machines.

6. Decision Trees and Random Forests

7. Neural Networks and Deep Learning

8. Unsupervised learning: Clustering (K-means, DB Scan, clustering metrics)

9. Dimensionality reduction: Principal Component Analysis (PCA).

10. Laboratory experiences: Implementation of selected algorithms and techniques in Python.

Planned learning activities and teaching methods: TTheoretical classes using both slides and blackboard. Problem solving sessions, involving students in the solution. Laboratory sessions in which the students will actively try to implemnt techniques and solve problems from the course under supervision.

The use of generative AI tools and Large Language Models (LLMs) as part of the learning process is strongly discouraged: the objective of the course is to allow students to think independently about machine learning problem and acquire basic competences. In this context, using AI offers a quick answer that sidesteps considering the trade-offs and effects of different choices, and makes the learning process shallower. The use of these tools during exams is strictly forbidden.

In addition to contacting the course instructor, students with disabilities, Specific Learning Disorders (SLD), Special Educational Needs (SEN), and other health conditions can reach out to the Student Services Office - Inclusion Unit to receive more information about opportunities to access teaching with specific support and tools.