Unit MACHINE LEARNING
- Course
- Programming and management of computer systems
- Study-unit Code
- A002051
- Curriculum
- In all curricula
- Teacher
- Valentina Franzoni
- Teachers
-
- Valentina Franzoni
- Hours
- 42 ore - Valentina Franzoni
- CFU
- 6
- Course Regulation
- Coorte 2023
- Offered
- 2024/25
- Learning activities
- Caratterizzante
- Area
- Tecnologie informatiche e dell'informazione
- Academic discipline
- INF/01
- Type of study-unit
- Obbligatorio (Required)
- Type of learning activities
- Attività formativa monodisciplinare
- Language of instruction
- Italian or English
- Contents
- Introduction to machine learning. Supervised, semi-supervised and unsupervised approaches.
Classification, clustering, anomaly detection. Applications to computer vision and natural language processing. Introduction to deep learning. Advanced neural network models. - Reference texts
- Stuart Russel, Peter Norvig, Artificial Intelligence: A Modern Approach, Global 4th Edition - Pearson - 2020
Tan, Steinbach, Karpatne, Kumar.
Introduction to Data Mining, 2nd Edition
2019. Pearson
Charu C. Aggarwal.
Neural Networks and Deep Learning: a text book. Springer 2018 - Educational objectives
- The student will get to know the main methods of machine learning according to the various supervised, semi-supervised and unsupervised approaches. He/she will also get to know some methods -typical and advanced- of deep learning, also applicable to computer vision and natural language processing problems, including large language models.
- Prerequisites
- Knowledge of artificial intelligence and programming is useful.
- Teaching methods
- Lectures and practical lessons.
- Other information
- The lecturer is available for examinations in Italian or English.
- Learning verification modality
- Oral examination and project. Possible intermediate tests during the course.
- Extended program
- Introduction to machine learning. Supervised, semi-supervised and unsupervised approaches.
Classification (decision trees, rule-based approach, naive bayes, nearest neighbours, SVM, neural networks). , clustering (k-means), anomaly detection. Applications to computer vision and natural language processing. Introduction to deep learning. Advanced models of neural networks (convolutional NN, transfer learning, generative models). Bias and ethics by design. - Obiettivi Agenda 2030 per lo sviluppo sostenibile
- This teaching contributes to the realisation of the UN goals
of the 2030 Agenda for Sustainable Development such as:
goal 4: quality education
goal 5: gender equality
goal 9: industry, innovation and infrastructure