ECTS credits ECTS credits: 6
ECTS Hours Rules/Memories Hours of tutorials: 1 Expository Class: 21 Interactive Classroom: 21 Total: 43
Use languages English
Type: Ordinary subject Master’s Degree RD 1393/2007 - 822/2021
Departments: Electronics and Computing, External department linked to the degrees
Areas: Computer Science and Artificial Intelligence, Área externa M.U en Intelixencia Artificial
Center Higher Technical Engineering School
Call: Second Semester
Teaching: With teaching
Enrolment: Enrollable | 1st year (Yes)
This course offers a comprehensive introduction to the most relevant techniques and architectures in deep learning. It covers the foundations (including regularization and optimization techniques), the classical deep learning models (convolutional networks, recurrent networks, autoencoders), and progresses to advanced models (GANs, diffusion models, transformers) as well as deep reinforcement learning. The approach is practical and up-to-date, enabling students to understand, implement, and apply these models in various contexts, while also becoming familiar with current challenges and future directions.
1. Introduction to deep learning: Shallow learning, Deep learning, Deep Learning libraries, Examples.
2. Regularization and optimization in deep learning: Introduction to regularization, Regularization via data, Regularization via model, Regularization via objective function, Optimization.
3. Convolutional neural networks (CNNs): Introduction to CNNs, Convolutional layer, Pooling layer, Fully connected layer, CNNs examples, Pretrained models, Residual networks, Inception networks, Xception networks.
4. Recurrent neural networks (RNNs): Sequence data, Using sequence data without recurrence, Simple recurrent networks, LSTM networks, GRU networks, Advanced use of RNNs.
5. Generative AI: Autoencoders, Generative Adversarial Networks (GANs), Diffusion Models, Transformers.
6. Reinforcement learning: Basics, What is Reinforcement learning, Solution methods.
Basic bibliography
· Chollet, Francois (2021). Deep Learning with Python. Manning, 2nd edition. Book.
· Elgendy, Mohamed (2020). Deep learning for vision systems. Manning Publications Co. Book.
· Géron, Aurélien (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow : concepts, tools and techniques to built intelligent systems. O'Reilly Media Inc, 3rd ed.. Book.
· Langr, Jakub, Bok, Vladimir (2019). GANs in Action : deep learning with generative adversarial networks. Manning. Book.
Supplementary bibliography
· Ferlitsch, Andrew (2021). Deep learning patterns and practices. Manning Publications. Book.
· Trask, Andrew W. (2019). Grokking deep learning. Manning. Book.
- Ability to implement, validate and apply a stochastic model starting from the observed data on a real system, and to perform a critical analysis of the obtained results, selecting those ones most suitable for problem solving
- Understanding and command of the main techniques and tools for data analysis, both from the statistical and the machine learning viewpoints, including those devised for large volumes of data, and ability to select those ones most suitable for problem solving
- Ability to outline, formulate and solve all the stages of a data project, including the understanding and command of basic concepts and techniques for information search and filtering in big collections of data
[- Knowledge of computer tools in the field of machine learning and ability to select those ones most suitable for problem solving
1. Personalized attention: Personalized attention to students includes not only tutorials (either virtual or in-person) to discuss questions, but also the following actions: monitor the work of laboratory practices proposed by the teacher, evaluate the results obtained in practice and seminars, and conduct personalized meetings to answer questions about the contents of the subject.
2. Laboratory practice: Laboratory activities are based on the knowledge that students are acquiring in lectures.
3. Objective test: A test shall be administered to assess the theoretical and practical knowledge acquired by students.
4. Guest lecture / keynote speech: Lectures explain the theoretical concepts using different digital resources.
1. Laboratory practice (50%): Practice exercises based on the knowledge acquired in the theoretical classes.
2. Objective test (50%): Test conducted at the end of the semester with theoretical and practical content.
To pass the course, it is essential to obtain a minimum grade of 4 in both parts separately. The final grade of the course will be the arithmetic mean of the continuous assessment and the final exam, except in cases where the minimum grade has not been reached in either part, in which case the final grade cannot exceed 4.
Submitting any of the activities or continuous assessment tests will imply that the student has chosen to take the course. Therefore, from that moment on, even if the student does not take the final exam, one opportunity will have been used.
In the second opportunity (July), the grades from the continuous assessment and/or the final exam obtained during the semester will be retained, provided that the grade in that part is 4 or higher. If the student takes the second opportunity in the continuous assessment or the final exam, the grade obtained in the first opportunity for that part is canceled, and the grade for that part will be the one obtained in the second opportunity. For continuous assessment, a deadline will be established for submitting the exercises. The final grade of the course in the second opportunity will be calculated using the same criteria as in the first opportunity.
Problem-based learning, seminars, case studies, and projects: These are sessions aimed at enabling students to acquire specific competencies through solving exercises, studying cases, and carrying out projects that require the application of knowledge and skills developed during the course. These sessions may require students to present their solutions orally. Student work can be done individually or in groups. 48 hours of dedication, 7 hours in-person.
Theoretical classes: Oral presentations complemented by audiovisual aids and some questions directed to students, with the aim of conveying knowledge and facilitating learning. In addition to the oral presentation time by the instructor, this
activity requires students to dedicate time to prepare and review the materials covered in the class. 42 hours of dedication, 21 hours in-person.
Laboratory practical classes: Classes focused on enabling students to carry out practical work that involves tackling complex problems, analyzing, and designing solutions as a means to resolve them. This activity may require students to present the work orally. Student work can be done individually or in groups. 60 hours of dedication, 14 hours in-person.
| Thursday | |||
|---|---|---|---|
| 15:30-17:00 | Grupo /CLIL_01 | - | IA.02 |
| 06.10.2026 16:00-20:00 | Grupo /CLE_01 | IA.12 |
| 06.10.2026 16:00-20:00 | Grupo /CLIL_01 | IA.12 |
| 07.07.2026 16:00-20:00 | Grupo /CLE_01 | IA.02 |
| 07.07.2026 16:00-20:00 | Grupo /CLIL_01 | IA.02 |