- Docente: Andrea Asperti
- Credits: 6
- SSD: INF/01
- Language: English
- Teaching Mode: Traditional lectures
- Campus: Bologna
- Corso: Second cycle degree programme (LM) in Computer Science (cod. 5898)
-
from Sep 18, 2023 to Dec 15, 2023
Learning outcomes
Machine learning deals with computer programs that extract features from data, and use them to solve predictive tasks, such as document classification, object recognition, anomaly detection, medical diagnosis, robot control, and so on. These programs, typically improve their performance through experience; they adapt to new tasks, related to previously encountered ones, solving them more efficiently. The course cover traditional topics such as decision tree learning, logistic regression, Bayesian networks and neural networks and introduces the recent field of deep learning.
Course contents
The course is divided into two main sections.
The initial part offers a comprehensive introduction to the field of machine learning, covering its typical forms: supervised, unsupervised, and reinforcement learning. It will delve into fundamental topics like decision tree learning, logistic regression, Bayesian networks, and Support Vector Machines.
The second segment of the course focuses specifically on Neural Networks and their prominent learning mechanism, the backpropagation algorithm. Students will explore various types of neural networks, including feedforward, convolutional, and recurrent networks, along with practical applications. Additionally, the course will delve into techniques for visualizing the impact of hidden units, which is closely related to concepts like deep dreams and inceptionism. Furthermore, students will be introduced to modern generative approaches, comprising Diffusion Models. The course will also briefly touch upon thematic topics such as Object Detection and Semantic Segmentation
Readings/Bibliography
Teacher's slides.
During the course, additional links to relevant documents and sites will be provided.
Teaching methods
Frontal lessons integrated with practical exemplifications
We also foresee additional laboratories held by tutors.
Assessment methods
Individual project on a topic defined by the teacher, possibly integrated by a written quiz.
Teaching tools
The course will make use of several opens source libraries for Machine Learning. In particular we shall mostly use
Office hours
See the website of Andrea Asperti