• University of Beira Interior

    MACHINE LEARNING


2023/24, Fall

NEWS

09/02/2024: The marks of the Exam (Recurso) are available. Tests can be seen on Friday, 10/02, 14:00-16:00.

25/01/2024: The marks of the Exam (Normal) are available. Tests can be seen on Friday, 26/01, 14:00-16:00.

10/01/2024: The marks of the written test and of the practical works are available. Tests can be seen on Thursday, 11/01, 14:00-16:00.

14/09/2023: 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. Support Vector Machines;

7. Unsupervised Classification;

8. Density Estimation;

9. 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 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 Regression) (5/20).

- Due Date: Monday, October 10th, 2023, 23:59:59.

- (P2) Practical Project 2: Supervised Learning (Classification) (5/20).

- Due Date: Monday, October 31st, 2023, 23:59:59.

- (P3) Practical Project 3: Convolutional Neural Networks - CNNs (5/20).

- Due Date: Monday, November 28th, 2023, 23:59:59.

- (P4) Practical Project 4: Unsupervised Learning (5/20).

- Due Date: Monday, December 19th, 2023, 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) Tuesday, January 9th, 2024, 14:00, Room 6.18.

- Mark (M) M = [A >= 0.8] * (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 Regression): [pdf]

Practical Project I (Medical Cost Personal Datasets, Kaggle): [zip]

Theoretical slides (Optimization; Linear Regression): [pdf]

Practical Sheet II (Linear Regression): [pdf]

Practical Sheet II Pizza Dataset): [csv]

Theoretical slides (Logistic Regression): [pdf]

Linear Regression (w/ TensorFlow): [py]

Practical Sheet III (Logistic Regression): [pdf]

Practical Sheet III (Wines Dataset): [csv]

Logistic Regression (w/ TensorFlow): [py]

Theoretical slides (Experimental Setup): [pdf]

Practical Sheet IV (Experimental Setup): [pdf]

Practical Sheet IV (Banknote Dataset): [csv]

Logistic Regression (w/ Keras): [py]

Practical Project II (MNIST multiclass classification Kaggle): [pdf]

Theoretical slides (Dimensionality Reduction): [pdf]

Practical Sheet V (Dimensionality Reduction): [pdf]

Practical Sheet V (AR Dataset): [csv]

Dimensionality Reduction (Tutorial, AR Dataset): [py]

Theoretical slides (Neural Networks, CNNs): [pdf]

Practical Project III (Convolutional Neural Networks - CNNs): [pdf]

Practical Project III (Help script): [py]

Practical Project III (AR): [zip]

Theoretical slides (Self Supervised Learning): [pdf]

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

Theoretical slides (Deep Learning Architectures): [pdf]

Theoretical slides (Unsupervised Learning): [pdf]

Practical Sheet VII (Unsupervised Learning): [pdf]

Practical Project IV (Unsupervised Learning): [pdf]

Practical Project IV Dataset (Credit Card Costumer): [zip]

Theoretical slides (Reinforcement Learning): [pdf]

Practical Sheet VIII (Reinforcement Learning): [pdf]





EVALUATION



FACULTY

HUGO PEDRO PROENÇA


Informatics Department

Theoretical + Practical classes