International Master in Computer Vision

Fundamentals of machine learning to computer vision.

Teachers:
Eva Cernadas: eva.cernadas@usc.es.
Jaime Cardoso: jaime.cardoso@fe.up.pt.

Alphabet of female women in Computer Science

Contents:

1. Machine learning theory (Jaime Cardoso)

2. Regression and optimization (Jaime Cardoso)

3. Introduction to model of sequential dates (Jaime Cardoso)

4. Classification: model selection and evaluation ( PDF)

5. Linear Discriminant Analysis (LDA) classifier ( PDF)

6. Artificial neural networks (ANN) ( PDF)

7. Support Vector Machine (SVM) ( PDF)

8. Ensembles ( PDF)

9. Unsupervised machine learning ( PDF)

Practical contents:

1. Machine learning and gender exercises (in the classroom)

2. Project (in the classroom)

Lab exercices:

During the master course FMLCV (Fundamentals of machine learning for computer vision), students will do different exercises in order to practice the practical contents of unsupervised and supervised classification models.

3. Classification: model selection and evaluation ( PDF)

4. Linear Discriminant Analysis (LDA) classifier ( PDF)

5. Artificial neural networks (ANN) (PDF)

6. Support Vector Machine (SVM) ( PDF)

7. Ensembles ( PDF)

8. Unsupervised machine learning ( PDF)

Bibliography:

1. Technical:

   1. R.O. Duda, P.E. Hart, D.G. Stork. Pattern classification. Wiley Interscience, 2000. ISBN: 978-0471056690

   2. Manuel Fernández-Delgado, Eva Cernadas, Senén Barro and Dinani Amorim, Do we Need Hundreds of Classifiers to Solve Real World Classification Problems? Journal of Machine Learning Research, 2014.

   3. Other articles that will be recommended during the course (in the classroom).

2. Machine learning, gender and ethics:

   1. Kate Crawford. Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Write about many aspects of the artificial intelligence with chapters dedicated to computer vision. 2022 (english). Spanish version (2023): https://doi.org/10.35869/god.v1i.5067

   2. Criado Pérez, Caroline . Invisible women: Exposing data bias in a world designed for men. Random House, 2019 (english). Spanish version: La mujer invisible: Descubre cómo los datos configuran un mundo hecho por y para los hombres. Seix Barral, 2020 (spanish).

   3. Catherine D'Ignazio and Lauren F. Klein. Data Feminism (online access to the book). The MIT Press, 2020. A new way to think about data science and ethics.

   4. El automágico traje del emperador (spanish). An experiment about the relation of the gender and the automatic algorithms in image understanding.

   5. How to keep human out of AI (english). Kriti Sharma explores how the lack of diversity in tech is creeping into our AI.

   6. Gendered innovations is a project promoted by Londa Schiebinger that harness the creative power of sex, gender, and intersectional analysis for innovation and discovery, and its importance in the research. It has sections for machine learning and robotics. For example the case of study Face recognition.

   7. Surveillance capitalism (traslated to spanish as “El capitalismo de vigilancia”) was a term invented by Shoshana Zuboff, who speaks the influence of survillance in the humans.

3. Notes about programming languages (in Galician language):

   1. Python: solved exercises and notes used in Physics degree.

   2. Matlab/octave: solved exercises and lectures used in Mathematics degree.