- Course
- 2024-2025
- Semester
- 1
- ECTS
- 6
- Type
- Compulsory
- University
- USC and UPorto
Subject objectives
The aim of the course is to present some of the topics which are at the core of modern Machine Learning, from fundamentals to state-of-the-art methods. Emphasis will be put both on the essential theory and on practical examples and lab projects. Each exercise has been carefully chosen to reinforce concepts explained in the lectures or to develop and generalize them in significant ways.
Contents
1. Machine learning teory.
2. Regression and optimization.
3. Introduction to model of sequential dates
4. Classification: model selection and evaluation
5. Artificial neural networks
6. Support vector machines (SVM)
7. Ensembles
8. Unsupervised machine learning
Basic and complementary bibliography
Basic:
Machine learning techniques: R.O. Duda, P.E. Hart, D.G. Stork. Pattern classification. Wiley Interscience, 2000. ISBN: 978-0471056690.
Do we Need Hundreds of Classifiers to Solve Real World Classification Problems? Manuel Fern ́andez-Delgado, Eva Cernadas, Senén Barro and Dinani Amorim. Journal of Machine Learning Reseach. 2014.
Other articles that will be recommended during the course.
Complementary:
Invisible women: Exposing data bias in a world designed for men. Carolina Criado Pérez, Random House, 2019.
Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Kate Crawford. 2021.
Competencies
Ability to work in team, organization and planning (CT2).
Ability to analyze and synthesize knowledge (CG1).
knowledge of the fundamentals of machine learning models applyed to computer vision (CE2).
Ability to develop simple machine learning systems depending on existing needs and apply the most appropriate technological tools (CB7, CG4).
Acquire the learning skills that allow to continue studying in a way that will be largely self-directed or autonomous (CB6, CG5).
Practice the profession with a clear awareness of its human, economic, legal and ethical dimension, with special attention to the gender inequality of machine learning models.
Teaching methodology
Participatory lectures, seminars and conferences, learning based on the resolution of practical cases and projects, autonomous work and independent study by students, group work and cooperative learning. Subjects will be covered both in participatory lectures, where students will have the chance to implement methods for themselves. During the lecture part, the course topics will be presented and discussed. The practical/lab periods will be used for solving exercises and for the development of the assignments. Students will be assigned individual homework assignments during the whole duration of the course, involving exercises, readings and summarization of selected texts.
Evaluation system
Continuous assessment: the students assignments will account for 65% of the final grade. Practical work will consist of one project covering the course topics. This will account for 35% of the final grade.
In case of exam fraud the «Normativa de avaliación do rendemento académico d@s estudant@s e de revisión de cualificacións». will be applied.
Studying time and personal work
Face-to-face work:
Blackboard lectures: 14h
Computer laboratory sessions: 25h
Assessment exams: 3h
Total: 42h
Personal work:
Autonomous study: 24h
Practical study: 96h
Total: 120h
Subject study recommendations
Attendance to the blackboard lectures and computer laboratory sessions, and solving the proposed exercises using the machine learning libraries employed on the laboratory. Read the articles recommended in the course.
Observations
The subject website includes the whole subject material: