MACHINE LEARNING
MACHINE LEARNING
| A.Y. | Credits |
|---|---|
| 2023/2024 | 9 |
| Lecturer | Office hours for students | |
|---|---|---|
| Valerio Freschi | Tuesday 09.00 -11.00 or on demand |
| Teaching in foreign languages |
|---|
|
Course with optional materials in a foreign language
English
This course is entirely taught in Italian. Study materials can be provided in the foreign language and the final exam can be taken in the foreign language. |
Assigned to the Degree Course
| Date | Time | Classroom / Location |
|---|
| Date | Time | Classroom / Location |
|---|
Learning Objectives
The aim the course is to provide the required elements for understanding the foundations of the learning problem, with respect to the main algorithms for regression and classification. In particular, the course aims at enabling:
1. To gain basic notions, foundations, and methodologies of automatic learning, both supervised and unsupervised.
2. To acquire adequate theroretical and applicative instruments typical of the field of machine learning.
3. To achieve skills for applying tools and methodologies to different problems and scenarios.
4. To obtain knowledge and competencies for using and adapting state of the art software systems for the solution of automatic learning problems.
Program
01 Introduction
01.01 Machine learning: motivations, problems, and introductory defintions
01.02 Learning typologies
02 Mathematical optimization
02.01 Zero order techniques
02.02 First order techniques
02.03 Second order techniques
03 Linear regression
03.01 Least squares cost function
03.02 Absolute deviation cost function
03.03 Regression quality metrics
03.04 Weighted regression
04 Binary linear classification
04.01 Logistic regression
04.02 Perceptron
04.03 Support Vector Machines
04.04 Binary classification quality metrics
05 Multi-class linear classification
05.01 One-versus-All and multi-class classification
05.02 Multi-class classification quality metrics
05.03 Stochastic and mini-batch learning
06 Unsupervised learning
06.01 Linear autoencoders
06.02 Dimensionality reduction and principal components analysis
06.03 Cluster analysis and the K-means algorithm
07 Feature engineering, feature selection, nonlinear learning
07.01 Feature engineering: histogram features, standard normalization
07.02 Feature selection by means of regularization
07.03 Nonlinear regression
07.04 Nonlinear classification
08 Feature learning
08.01 Universal approximators
08.02 Generalization and overfitting
08.03 Cross validation, regularization
09 Elements of neural networks
09.01 Fully connected networks
09.02 Activation functions
09.03 Backpropagation algorithm
10 Laboratory activity
10.01 Introduction to Python, Numpy, Scikit-learn
10.02 Lab activity on linear regression
10.03 Lab activity on linear classification: logistic regression, SVM
10.04 Lab activity on unsuperivsed learning: PCA, K-means
10.05 Lab activity on neural networks
Bridging Courses
There are no mandatory prerequisites.
Learning Achievements (Dublin Descriptors)
Knowledge and understanding:
at the end of the course, the student will learn: the foundations to understand automatic learning problems, the design and analysis of the main supervised and unsupervised learning algorithms.
Applying knowledge and understanding:
the student will be able to understand the main features of the most common learning problems, and the related techniques for their solution. She/he will also be able to apply this knowledge for designing basic machine learning algorithms and the corresponding software systems.
Making judgements:
the student will be able to determine the adequacy and effectiveness of of machine learning algorithms and methodologies, particularly with respect to regression and classification problems.
Communication skills:
the student will learn to illustrate in a proper way the main learning techniques and to describe the factors affecting their effectiveness, with respect to specific application domains; in particular, she/he will critically reason through a given mathematical descriptive language introduced during the course.
Learning skills:
at the end of the course, the student will gain a good autonomy level in critically understanding study materials regarding the main issues in machine learning, that will also enable to deal with novel design scenarios to which apply the achieved knowledge.
Teaching Material
The teaching material prepared by the lecturer in addition to recommended textbooks (such as for instance slides, lecture notes, exercises, bibliography) and communications from the lecturer specific to the course can be found inside the Moodle platform › blended.uniurb.it
Supporting Activities
Multiple choice questions and solved exercises for the self-evaluation of the student preparation available inside the Moodle platform for blended learning.
Teaching, Attendance, Course Books and Assessment
- Teaching
Theory lectures and laboratory exercises.
The course is delivered in mixed mode, i.e. the lessons take place simultaneously in the classroom and remotely within the Moodle platform.
- Attendance
Although recommended, course attendance is not mandatory.
- Course books
Jeremy Watt, Reza Borhani, Aggelos Katsaggelos: "Machine Learning Refined. Foundations, Algorithms, and Applications", Cambridge University Press, (2020).
Andreas Lindholm, Niklas Wahlström, Fredrik Lindsten, Thomas B. Schön: "Machine Learning - A First Course for Engineers and Scientists", Cambridge University Press, (2022).
- Assessment
Learning achievements will be evaluated through a project and an oral exam.
The project, to be previously agreed with the teacher, has to be developed by groups composed of one or preferably two students and has to be submitted at least 10 days before the oral exam. The project is passed if the mark is at least 18/30; the mark is valid, even if the oral exam is taken but not passed, for the whole academic year. The aim of the oral examination is to verify learning and application skills, knowledge and understanding, learning autonomy and communication skills.
The oral exam, which can be taken only if the project has been passed (mark greater or equal than 18/30) consists of a discussion of the project and two questions on the course program. The final mark is the weighted average of the project and the oral exam (30% project, 70% oral exam). The oral exam is evaluated according to the following criteria: achieved knowledge, understanding of the basic principles of the subject, capability of presenting the topic in a rigorous manner.
- Disabilità e DSA
Le studentesse e gli studenti che hanno registrato la certificazione di disabilità o la certificazione di DSA presso l'Ufficio Inclusione e diritto allo studio, possono chiedere di utilizzare le mappe concettuali (per parole chiave) durante la prova di esame.
A tal fine, è necessario inviare le mappe, due settimane prima dell’appello di esame, alla o al docente del corso, che ne verificherà la coerenza con le indicazioni delle linee guida di ateneo e potrà chiederne la modifica.
Additional Information for Non-Attending Students
- Teaching
As for attending students.
- Attendance
As for attending students.
- Course books
As for attending students.
- Assessment
As for attending students.
- Disabilità e DSA
Le studentesse e gli studenti che hanno registrato la certificazione di disabilità o la certificazione di DSA presso l'Ufficio Inclusione e diritto allo studio, possono chiedere di utilizzare le mappe concettuali (per parole chiave) durante la prova di esame.
A tal fine, è necessario inviare le mappe, due settimane prima dell’appello di esame, alla o al docente del corso, che ne verificherà la coerenza con le indicazioni delle linee guida di ateneo e potrà chiederne la modifica.
| « back | Last update: 20/11/2023 |
