• University of Beira Interior

    MACHINE LEARNING


2025/26, Fall

Informatics Engineering (M.Sc.), Artificial Intelligence and Data Science (B.Sc.)


NEWS

09/02/2026: The 'Recurso exam epoch' marks are available. Tests can be seen on Tuesday, 10/02, between 14:00-15:00.

26/01/2026: The 'Normal exam epoch' marks are available. Tests can be seen on Tuesday, 27/01, between 14:00-15:00.

27/12/2025: The final 'Classific. Ensino/Aprendizagem' marks are available.

27/12/2024: The marks of the written test are available. The discussion of the practical works is scheduled. Tests can be seen on Monday, 05/01, during the afternoon.

01/09/2025: The webpage for the course is online.



PROGRAM

1. Introduction;

2. Model Representation, Linear Regression;

3. Logistic Regresion;

4. Dimensionality Reduction;

5. Neural Networks;

6. Unsupervised and Self-Supervised Learning;

7. Density Estimation;

8. Reinforcement Learning;


BIBLIOGRAPHY

- C. Bishop. Pattern Recognition and Machine Learning, Springer, ISBN-13: 978-0387310732, 2011.

- M. Mohri, A. Rostamizadeh, A. Talwalkar, F. Bach. Foundations of Machine Learning, ISBN-13: 978-0262039406, 2018.


EVALUATION CRITERIA

- Assiduity (A) To get approved at this course, students should attend to - at least - 80% of the theoretical and 80% of the practical classes.

- Practical Projects (P) The practical projects of this course weight 50% (10/20) of the final mark.

- (P1) Practical Project 1: Supervised Learning (Linear + Logistic Regression) (5/20).

- Due Date: Friday, October 3rd, 2025, 23:59:59.

- (P2) Practical Project 2: Convolutional Neural Networks - CNNs (10/20).

- Due Date: Friday, November 14th, 2025, 23:59:59.

- (P3) Practical Project 3: Unsupervised Learning (5/20).

- Due Date: Friday, December 12th, 2025, 23:59:59.

- To get approved at the course, a minimal mark of 8/20 should be obtained in the practical project part.

- Written Test (F) Thursday, December 18th, 2025, 18:00, Room 6.03.

- Mark (M) M = [A >= 0.8] * [P >= 8/20] * (P * 10/20 + F * 10/20).

- Admission to Exams Students with M >= 6 are admitted to final exams.

- The practical projects mark is considered in all examination epochs.




CLASSES

Theoretical slides (Introduction, Taxonomy ML): [pdf]

Practical Sheet I (Google Colab + Python essentials): [pdf]

Practical Project I (Linear + Logistic Regression): [pdf]

Practical Project I (Medical Dataset): [zip]

Practical Project I (MNIST Dataset): [zip]

Theoretical slides (Supervised Classification): [pdf]

Practical Sheet II (Linear Regression): [pdf]

Pizza Dataset: [csv]

Linear Regression (solution) [py]

(P1 Submission Deadline: October, 3rd, 23:59:59, hugomcp@ubi.pt)

Theoretical slides (Supervised Classification): [pdf]

Practical Sheet II (Logistic Regression): [pdf]

Wines Dataset: [csv]

Theoretical slides (MLPs): [pdf]

Practical Sheet IV (MLPs/CNNs): [pdf]

CIFAR-10: [zip]

Fashion MNIST: [zip]

Fashion MNIST Feature Extraction (Help): [py]

Theoretical slides (Dimensionality Reduction): [pdf]

Practical Sheet V (Dimensionality Reduction): [pdf]

Breast Cancer Dataset: [csv]

Theoretical slides (CNNs): [pdf]

Experimental Setup: [pdf]

Practical Shhet VI (Experimental Setup): [pdf]

AR Dataset: [zip]

Pratical Project II (CNNs): [pdf]

GTSRB Dataset: [zip]

Theoretical slides (Deep Learning Architectures and Learning Paradigms): [pdf]

Practical Sheet VII (Self Supervised Learning): [pdf]

(P2 Submission Deadline: November, 14th, 23:59:59, hugomcp@ubi.pt)

Theoretical slides (Unsupervised Learning): [pdf]

Practical Sheet VIII (Unsupervised Learning): [pdf]

(SOMs, cont):

Pratical Project III (Unsupervised Learning): [pdf]

Theoretical slides (RNNs): [pdf]

Practical Sheet X (RNNs): [pdf]

Example RNN: [py]

Examples Previous Exams: [zip]

Experimental Setup: [pdf]

Theoretical slides (Transformers): [pdf]

(P3 Submission Deadline: December, 12th, 23:59:59, hugomcp@ubi.pt)

Theoretical slides (Reinforcement Learning): [pdf]

Practical Sheet IX (Reinforcement Learning): [pdf]

(Written Test, December, 18th, 18:00, Room 6.03.)





EVALUATION



FACULTY

HUGO PEDRO PROENÇA


Informatics Department

Theoretical + Practical classes