ECTS credits ECTS credits: 3
ECTS Hours Rules/Memories Expository Class: 10 Interactive Classroom: 11 Total: 21
Use languages English
Type: Ordinary subject Master’s Degree RD 1393/2007 - 822/2021
Departments: Electronics and Computing
Areas: Computer Science and Artificial Intelligence
Center Higher Technical Engineering School
Call: Second Semester
Teaching: With teaching
Enrolment: Enrollable | 1st year (Yes)
The main objective of this subject is to train students in the development of skills for an adequate treatment of privacy, reliability, transparency and interpretability of models and results associated with intelligent systems. Special emphasis will be placed on identifying and analyzing biases and their impact on the design of Artificial Intelligence (AI) algorithms. In addition to technical aspects, disruptive technologies and specific and general computer tools, aimed at covering all phases of the design, analysis and evaluation of intelligent systems, students will learn to know and understand the social and ethical implications of technology in general and of AI in particular.
Explainability and interpretability. Model-agnostic methods. Explanations based on examples. FAT-E (fairness, accountability, transparency and ethics). Study and types of biases. Types and models of explanation. Evaluation methodologies. Data integrity, privacy, confidentiality and robustness
of models. Reliability by design.
Supplementary material will be provided in the virtual platform of the master to facilitate following each unit in this subject. Given the heterogeneity of topics to be dealt within this subject, with each class, references to bibliographic resources as well as other types of content (reports, multimedia, etc.) will be provided to student for the more specific aspects of the subject. The following references are of a complementary type, they deal with general aspects related to explainable and trustworthy AI.
1. V. Dignum. Responsible Artificial Intelligence. How to Develop and Use AI in a Responsible Way. Springer Nature Switzerland AG, 2019, ISBN: 978-3-030-30370-9, https://doi.org/10.1007/978-3-030-30371-6
2. A. Barredo Arrieta et al., Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI, Information Fusion, 58:82-115, Elsevier 2020, https://doi.org/10.1016/j.inffus.2019.12.012
3. T. Miller, Explanation in artificial intelligence: Insights from the social sciences. Artificial Intelligence, 267:1-38, Elsevier 2019, https://doi.org/10.1016/j.artint.2018.07.007
4. G. Vilone, L. Longo, Notions of explainability and evaluation approaches for Explainable Artificial Intelligence, Information Fusion, 76:89-106, Elsevier 2021, https://doi.org/10.1016/j.inffus.2021.05.009
5. R. Guidotti, A. Monreale, S. Ruggieri, F. Turini, F. Giannotti, D. Pedreschi, A Survey of Methods for Explaining Black Box Models, ACM Computing Surveys, 51(5):1–42, 2019, https://dl.acm.org/doi/10.1145/3236009
6. J.M. Alonso, C. Castiello, L. Magdalena, C. Mencar, Explainable Fuzzy Systems. Paving the way from interpretable fuzzy systems to explainable AI systems. Springer International Publishing, 2021, ISBN: 978-3-030-71098-9, https://doi.org/10.1007/978-3-030-71098-9
Contribute to the achievement of the competences associated with the MSc Degree in Artificial Intelligence to be taught jointly at the University of Coruña, the University of Santiago de Compostela, and the University of Vigo, especially:
1) General skills
CG1 - Maintain and extend theoretical approaches to allow the introduction and exploitation of new and advanced technologies in the field of Artificial Intelligence.
CG3 - Search and select the useful information that is necessary to solve complex problems, managing with ease the bibliographic sources of the field.
2) Basic skills
CB6 - Possess and understand knowledge that provides a foundation or opportunity to be original in the development and/or application of ideas, often in a research context.
CB7 - Students know how to apply the acquired knowledge and the ability required to solve problems in new or little-known environments within broader (or multidisciplinary) contexts related to their area of study.
CB8 - Students are able to integrate knowledge and face the complexity of formulating judgments based on information that, being incomplete or limited, includes reflections on the social and ethical responsibilities linked to the application of their knowledge and judgments.
CB9 - Students know how to communicate their conclusions as well as the acquired knowledge and ultimate reasons that support them to specialized and non-specialized audiences in a clear and unambiguous way.
3) Transversal skills
CT2 - Master the oral and written expression and comprehension of a foreign language.
CT3 - Use the basic tools of information and communication technologies (ICT) necessary for the exercise of their profession and for long-term learning in their lives.
CT4 – Develop the required skills for the exercise of a respectful citizenship with the democratic culture, human rights and the gender perspective.
CT6 - Acquire life skills and healthy habits, routines, and lifestyles.
CT8 – Recognize the importance of research, innovation and technological development in the socioeconomic and cultural progress of society.
4) Specific skills
CE5 - Ability to design and develop intelligent systems through the application of inference algorithms, knowledge representation and automatic planning.
CE6 - Ability to recognize those problems that require a distributed architecture that is not predetermined during system design, which will be suitable for the implementation of intelligent multi-agent systems.
The teaching methodology will be based on the individual work of the students, on the discussion with the teacher in class and on individual tutorials. There will be two types of classes:
1) Theory classes (expository): Oral presentation complemented with the use of audiovisual media and the introduction of some questions addressed to students, in order to transmit knowledge and facilitate learning. In addition to the oral presentation, students should dedicate some time to prepare and review the class materials on their own.
2) Practical laboratory classes (interactive): Students develop practical work that involves dealing with the resolution of complex problems, and the analysis and design of solutions that constitute a means for their resolution. Students may have to present their work orally. The work done by the students can be done individually or in work groups.
For each theme or thematic module of the expository classes, the teaching staff will prepare the contents, explain the objectives of the theme to the students in class, present each theme with the aim of providing a set of information with a specific scope, suggest a bibliography, provide additional work material, etc. This teaching methodology will be applied to the training activity "Theory classes".
Theory classes are aimed for developing skills CG1, CG3, CB6, CB7, CB8, CB9, CE5, CE6, CE7, CE8, CE9. In addition, the teaching staff will propose to the students a set of activities to carry out, individually or in groups (case studies, papers, presentations, readings, etc.). Students must submit a selection of them for evaluation. As a result, students will develop the skills CG3, CB7, CB8, CB9, CT2, CT3, CT4, CT6, CT8, CE7, CE8.
The interactive classes will take place in the selected Computer Classroom at each University, using various software tools for each of the thematic blocks, addressing exercises and projects with different levels of complexity. The students will work in individual positions with the constant support of the teaching staff. The scripts of the practices will be self-explanatory, allowing students to take profit of their personal work hours. Practical classes are aimed for developing skills CG1, CG3, CB6, CB7, CB8, CT3, CT8, CE5, CE6, CE7, CE8, CE9. Students can work on the solution to the problems raised individually or in groups. This teaching methodology will be applied to the training activity "Practical laboratory classes" and may be also applied to the training activity of "Problem-based learning sessions, seminars, case studies and projects".
Laboratory practices: the teaching staff of the subject poses to the students problems of a practical nature whose resolution requires the understanding and application of the theoretical-practical contents included in the contents of the subject.
Learning by projects: students are presented with practical projects whose scope requires an important part of the total dedication of the student in this subject. In addition, due to the scope of the work to be carried out, it is required that the students apply technical and non-technical skills.
Teaching will be supported by the virtual platform of the master in the following way: repository of documentation related to the subject (texts, presentations, etc.) and virtual tutoring of students (e-mail and forums).
Tutoring: the teaching staff will assist students in individualized tutorial sessions dedicated to study orientation and the resolution of doubts about the contents and work of the subject.
The evaluation of the learning considers an exam of the theoretical part (45%) and the evaluation of the deliveries associated with the interactive sessions (35%), the delivery of a personal work and its oral presentation (15%) and the continuous assessment of each student throughout the course (5%).
It is mandatory to pass all parts (exam, practices, work, continuous evaluation), considering the following criteria:
1. Exam (45%): The theoretical content of the subject will be evaluated in a single exam to be taken on the official date. The exam will consist of questions related to all the topics of the program. The exam will be specially oriented to evaluate the comprehension of the knowledge exposed in the theory classes. The exam grade will be the weighted average of the modules of the subject, which will only be calculated in the case of having a grade equal to or greater than 4 in each module.
2. Practices (35%): There will be mandatory deliveries associated with the interactive sessions related to each theoretical module. The solutions proposed by the students to the proposed practices will be evaluated. The evaluation of practices can be carried out through a correction by the teacher, or a defense of the solution provided by the student in the form of an oral presentation of the solution developed. (Applicable to the results of the training activities "Practical laboratory classes", "Problem-based learning, seminars, case studies and projects" and "Carrying out supervised work"). The average grade will only be calculated in the case of having a grade greater than or equal to 4/10 in all deliveries. In addition, it is mandatory face-to-face attendance of at least 60% of the interactive classes.
3. Work (15%): Students must submit and present a personal work according to the calendar established at the beginning of the semester. The evaluation of the supervised work will be carried out by means of a defense in which the students explain their proposal and conclusions to the teacher, or by means of an oral presentation of the solution in front of the classroom. The grade obtained will be the average of the evaluation of the written work and its oral presentation. The average will only be made if a grade equal to or greater than 4 is obtained in each part.
4. Continuous evaluation (5%): The attendance and active participation of students will be taken into account in the expository classes but also during the presentation of works, discussions, seminars, and in the interactive sessions that are held throughout the course. It is mandatory attending at least 60% of the presentation sessions and seminars.
The final grade for the subject will be the sum of the four partial grades, except in those situations indicated above. When any part is not passed, the final grade for the opportunity will be the minimum of the partial grades.
Students who have not participated in any of the evaluation activities will obtain the grade of not presented.
Students who have official exemption from class attendance must take, in any case, the final written exam, as well as doing all deliveries of practices and work that are established as mandatory throughout the course and, if required, make their oral presentations. In this modality, the tutoring, deliveries and oral presentations can be made remotely.
In the second opportunity, the students must pass the pending evaluation activities of the first opportunity, in accordance with the previous criteria.
For cases of fraudulent completion of exercises or tests, the provisions of the Regulations for evaluating the academic performance of students and reviewing grades will apply. The total or partial copy of any practice or theory exercise will automatically mean a grade of 0.0 in the subject and opportunity.
This subject has 3 ECTS credits, corresponding to a total workload of 75 hours. This time can be divided as follows:
In person classroom work time: 22 total hours, divided into 10h (expository classes, seminars, oral presentations and associated discussion), 11h (interactive classes in the laboratory), and 1h (tutoring).
Personal work time: 53 total hours, divided into 38 hours (autonomous study of theory and practice) and 15 hours (work, projects and other activities).
It is recommended to bring the subject up to date and the use of tutoring sessions to clarify doubts and get advise on its development. In addition, it is recommended that students solve, verify and validate all the exercises and practices proposed during the course (no matter if they are or not to be officially evaluated).
Media complementary to teaching: virtual course on the virtual platform of the master, prepared and constantly updated by the teaching staff of this subject.
The teaching of this subject will be in English. The expository teaching (10h) will be given by USC and broadcasted for all students. There will be a specific interactive teaching group at each university (11h).
Jose Maria Alonso Moral
Coordinador/a- Department
- Electronics and Computing
- Area
- Computer Science and Artificial Intelligence
- Phone
- 881816432
- josemaria.alonso.moral [at] usc.es
- Category
- Professor: University Lecturer
| Tuesday | |||
|---|---|---|---|
| 17:00-18:30 | Grupo /CLE_01 | English | IA.12 |
| 18:30-20:00 | Grupo /CLIL_01 | English | IA.12 |
| 05.26.2025 16:00-20:00 | Grupo /CLIL_01 | IA.02 |
| 05.26.2025 16:00-20:00 | Grupo /CLE_01 | IA.02 |
| 06.30.2025 16:00-20:00 | Grupo /CLIL_01 | IA.02 |
| 06.30.2025 16:00-20:00 | Grupo /CLE_01 | IA.02 |