Aprendizaje automático

The subject introduces students to machine learning techniques. In particular, it aims for students, by the end of the course, to be able to:

- Know and understand the fundamental concepts of machine learning for IoT.
- Implement supervised/unsupervised machine learning algorithms with classical and deep neural networks.
- Apply the acquired knowledge and solve problems in new or unfamiliar environments within broader and multidisciplinary contexts, being able to integrate knowledge.

- Introduction to both machine learning and methodologies for ML model development.
- Data preprocessing and dimensionality reduction techniques.
- Supervised learning: Classification and regression.
- Unsupervised learning.
- Reinforcement learning.
- Artificial Neural Networks and Deep Learning.
- Introduction to edge learning and distributed/federated learning.

Basic bibliography

[1]. Alpaydin, E. (2010). Introduction to machine learning. MIT press.
[2]. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction. Second edition. Cambridge (Massachusetts): MIT Press.
[3]. Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2021). Dive into deep learning. arXiv preprint arXiv:2106.11342.
[4]. Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019). Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 10(2), 1-19.

Complementary bibliography

[1]. Brink, H., Richards, J., & Fetherolf, M. (2017). Real-world machine learning. Shelter Island, NY: Manning
[2]. Yang Q., Liu Y., Cheng Y., Kang, Y, Chen T. Yu H. (2020). Federated Learning. Springer, https://doi.org/10.1007/978-3-031-01585-4.

The degree program outlines the following competencies for this course:

- Integrate technologies such as Machine Learning, Big Data processing, Distributed Ledger Technologies (DLT), edge computing, among others, for the development of smarter and more efficient IoT systems.

The contents of the course will be taught indistinctly between lectures and interactive classes. The completion of all the proposed activities is necessary to pass the course.

Lecture Classes (theory): they will consist of explaining the different sections of the course syllabus, with the help of electronic media (presentations, videos, etc.).

Interactive classes (laboratory): different practical problems related to the content of the subject will be posed for the student to solve individually or in groups.

Autonomous work: the scope and objectives of the projects, use cases and/or practical problems may require autonomous work on the part of the students, albeit under the supervision of the teaching staff.

Office hours: Office hours will be used to solve students' doubts related to the contents of the subject. These office hours can be both face-to-face and virtual (via email, virtual campus or video conferencing platforms). Synchronous office hours will require a prior appointment.

First Call
To pass the course, the student must complete and pass the proposed practical (35%) and supervised (25%) work, which represents 60% of the final grade, as well as pass the final exam, which constitutes the remaining 40%. To do this, it is necessary to obtain a grade equal to or higher than 5 in the overall assessment. Additionally, it is required to achieve at least a 4 in each evaluated part to average.
The final exam questions will focus on the specific content developed in the course in relation to its competencies and may have been acquired by the student in both the lecture and interactive parts.

Mid-term Exams: No mid-term exams will be conducted.


Second call
The qualification obtained in the laboratory part (practical and supervised work) during the course as well as its weight in the final grade are maintained. Students who did not reach the cutoff qualification in the proposed activities during the previous call may submit similar activities to those not passed, which will be proposed by the professors, before the final exam of the second opportunity. Once all the evaluated parts are separately passed, the exam will account for 40% of the final grade, and the laboratory part will constitute the remaining 60% (practical work 35% and supervised work 25%). To pass the course, a global average grade of 5 or higher is necessary. Additionally, it is required to achieve at least a 4 in each evaluated part to average.

The final exam questions will focus on the specific content developed in the course in relation to its competencies and may have been acquired by the student in both the lecture and interactive parts.

Repeating students:
In case of repeating students, they will be examined under the same conditions as students in the first round.

No-show qualification:
The student will receive the qualification of "no-show" when he/she does not take the final exam.

Fraudulent performance of exercises or tests:
In cases of fraudulent conduct in exercises or tests, the official performance evaluation regulations of each institution will apply. In particular, if any form of plagiarism is detected in any tests or exams, the final grade will be FAIL (0), and the incident will be reported to the appropriate academic authorities.

According to the master's program outline, the course has a workload of 4.5 ECTS. Given that 25 hours are allocated per ECTS, the total workload for the course is 112.5 hours (4.5 ECTS x 25 hours per ECTS).
The workload includes 24 hours of lecture classes and 12 hours of laboratory classes. Therefore, personal study time for students should account for 76.5 hours.

The student should keep up to date with the content subject in order to be able to apply the knowledge acquired in theory in laboratory exercises.

Primary language: the subject will be taught in Spanish.