
Artificial Intelligence
Code: 101764Credits: 6
| Degree programme | Type | Course |
|---|---|---|
| Aeronautical Management | OB | 3 |
Contact lecturer
- Name :
- Olivier Penacchio
- Email :
- oliver.penacchio@uab.cat
Group languages
You can consult this information at the end of the document.
Prerequisites
To be able to do the practical exercises of the course it is necessary to have the adequate knowledge of programming in Python language that is provided in Fundamentals of Computer Science and Advanced Computing.
Therefore, IN CASE OF NOT HAVING PASSED THE COURSE OF FUNDAMENTALS OF COMPUTERS PREVIOUSLY AND/OR NOT HAVING REGISTERED FOR ADVANCED COMPUTING IN THE CURRENT YEAR, IT IS STRONGLY RECOMMENDED NOT TO REGISTER FOR THIS COURSE THIS YEAR.
For the theoretical part of the course, some minimum knowledge of statistics (1st year) and algebra (2nd year) are also necessary.
In the case of students in the Business and Technology degree, it is recommended that they have passed the courses of their degree equivalent to those mentioned for the Aeronautical Management students.
Objectives
The objectives of the course can be summarised as follows:
- Describe the main areas of artificial intelligence.
- Describe the fundamental techniques of knowledge representation, learning, and search for problem solving.
- Recognise situations in which the application of artificial intelligence is appropriate for solving problems in the aeronautical sector.
- Analyse a problem and design an optimal solution by applying the techniques covered in the course.
- Implement the basic algorithms required to solve the proposed problems.
- Evaluate the results of the implemented solution and identify possible improvements.
- Justify and defend the decisions made in the proposed solutions.
- Acquire the fundamental knowledge required to understand modern artificial intelligence techniques in a rapidly evolving field.
- Identify the main ethical challenges associated with the development and application of artificial intelligence and evaluate their implications.
The course Artificial Intelligence is part of the subject area Information Technologies in the Aeronautical Sector, together with the courses Advanced Computing and Analysis and Design of Information Systems. Owing to its content, this subject area is closely related to the first-year course Fundamentals of Computing.
The objectives of the course can be summarised as follows:
Knowledge
- Describe the main areas of artificial intelligence.
- Describe the fundamental techniques of knowledge representation, learning, and search for problem solving.
- List the essential steps of the different algorithms presented.
- Identify the advantages and limitations of the algorithms covered in the course.
- Relate artificial intelligence techniques to their applications in the aeronautical sector.
Skills
- Recognise situations in which the application of artificial intelligence is appropriate for solving a problem.
- Analyse a problem and design an optimal solution by applying the techniques learned.
- Prepare technical documentation related to the analysis and solution of a problem.
- Implement the basic algorithms required to solve the proposed problems.
- Evaluate the results of the implemented solution and identify possible improvements.
- Justify and defend the decisions made in the proposed solutions.
Learning outcomes
- KM22 (Define the use of artificial intelligence in airport and airline management, identifying technological challenges in the representation of knowledge, reasoning, machine learning and process optimisation.) Define the use of artificial intelligence in airport and airline management, identifying technological challenges in the representation of knowledge, reasoning, machine learning and process optimisation.
Contents
- Introduction to Artificial Intelligence
- Problem Solving and Search
- Problem Solving and Search
- Problem Solving and Search
- Automated Reasoning and Logic
- Reasoning under Uncertainty
- Knowledge Representation
- Machine Learning
- Machine Learning
- Neural Networks
- Large Language Models (LLMs) and Generative Artificial Intelligence
- Large Language Models (LLMs) and Generative Artificial Intelligence
Learning activities and methodology
| Title | Hours | ECTS | Learning outcomes |
|---|---|---|---|
| Preparation of theory lectures | 10 | 0.4 | KM22 |
| Personal study | 30 | 1.2 | KM22 |
| Preparation and discussion of topics related to the practical tasks | 15 | 0.6 | KM22 |
| Theory and discussion classes | 22 | 0.88 | KM22 |
| Laboratory classes | 10 | 0.4 | KM22 |
| Group study | 45 | 1.8 | KM22 |
| Problems classes | 12 | 0.48 | KM22 |
The Campus Virtual platform (http://cv.uab.cat) will be the usual tool for exchanging information between teaching staff and students. All materials and information related to the development of the subject will be published on this platform.
The activities that will be carried out in the subject are organized as follows:
Theory classes
Two main methodologies will be followed:
- Participatory master class where the main concepts and algorithms of each subject will be presented, and examples and short exercises will be proposed so that students can put into practice specific aspects of the subjects presented.
- Inverted classroom where exercises and problems will be carried out that will have to be handed in at the end of the class. Before class, you will need to do some preparatory work such as watching a video, reading a document or answering a quiz.
Classes of problems
Exercises will be proposed to be solved in small cooperative groups in order to consolidate the learning of the topics presented in the theory classes. Depending on the topic, some of these exercises will be solved with programs. The work will be done in groups that will change for each delivery.
Practice classes
In practice classes, the most practical part of the tasks will be worked on. Solutions and feedback will be discussed in detail and attention will be given to each group through interviews and peer review. To check that each student in the group has understood each part of the solution given, there will be control sessions with compulsory attendance.
Assessment
Continuous assessment activities
| Title | Weight | Hours | ECTS | Learning outcomes |
|---|---|---|---|---|
| Written exam of Part 2 | 25% | 2 | 0.08 | KM22 |
| Written exam of Part 1 | 25% | 2 | 0.08 | KM22 |
| Verification of group assignments | 50% | 2 | 0.08 | KM22 |
This course does not offer a single-assessment option. Assessment is based on continuous evaluation, allowing students to monitor their progress throughout the course.
There will be one assignment for each topic, which may include written exercises and programming tasks. Assignments will be completed in groups.
The assignments collectively contribute 50% of the final grade.
There will be two written examinations during the course, each contributing 25% of the final grade.
There are no minimum passing grades for individual assessment components, except for the overall final grade. A final grade of 5.0 is required to pass the course.
Resit procedure: Both written examinations are eligible for resit. Students may take the resit examination provided they have completed assessment activities representing at least two-thirds of the total course grade. Only students whose weighted average across all assessment activities is at least 3.5 will be eligible for the resit examination.
Criteria for Honours (Matrícula d’Honor): The award of a Matrícula d’Honor is at the discretion of the course instructors. According to UAB regulations, this distinction may only be awarded to students who obtain a final grade of 9.0 or higher. The number of honours awarded may not exceed 5% of the students enrolled in the course.
Criteria for a "Not Assessable" (NA) grade: A student will be considered Not Assessable (NA) only if they have not taken any of the written examinations.
Assessment schedule: The dates for continuous assessment activities and assignment submissions will be published on the course website and the Virtual Campus. These dates may be subject to change due to unforeseen circumstances. Any changes will be communicated through the course website and the Virtual Campus, which are considered the official channels of communication between instructors and students.
Review procedure: For each assessment activity, a date, time, and location will be announced for students to review their work with the instructor. Students may raise questions or appeal their grade during this review session. If a student does not attend the scheduled review, no subsequent review of that assessment will be possible.
Use of AI tools (e.g. ChatGPT): The use of AI tools is prohibited only during written examinations. Outside examinations, students are expected to use these tools critically and responsibly, as aids to learning rather than as a means of copying or replacing their own work.
Academic integrity and plagiarism: Without prejudice to any additional disciplinary measures that may be deemed appropriate, and in accordance with current academic regulations, any irregularity committed by a student that may affect the assessment of an evaluable activity will result in a grade of zero (0) for that activity. Assessment activities penalised in this way are not eligible for resit. If passing the affected activity is required to pass the course, the student will automatically fail the course without the possibility of passing it through the resit process during the same academic year.
Such irregularities include, but are not limited to:
- Copying all or part of a laboratory exercise, report, or any other assessment activity.
- Allowing another student to copy one's work.
- Submitting group work that has not been completed entirely by the members of the group (this applies to all members of the group, not only those who did not contribute).
- Submitting materials prepared by a third party as one's own work, including translations or adaptations, or more generally any work containing elements that are not the student's own original contribution.
- Having communication devices (such as mobile phones, smartwatches, camera pens, etc.) accessible during individual written examinations.
- Communicating with other students during individual written examinations.
- Copying or attempting to copy from another student during an examination.
- Using or attempting to use unauthorised written materials during an examination.
If a student commits an irregularity in an assessment activity, the numerical grade recorded on the transcript will be the lower of 3.0 or the weighted average of all assessment grades. Consequently, it will not be possible to pass the course by compensation.
In summary: copying, facilitating copying, or committing plagiarism in any assessment activity will result in a FAILwith a final grade of less than 3.0.
Bibliography
S. Russell and P. Norvig. Artificial Intelligence: A Modern Approach. Fourth Edition. Prentice Hall, 2021.
(A Spanish translation is available: Inteligencia artificial: Un enfoque moderno.)
Christopher M. Bishop. Pattern Recognition and Machine Learning. Springer-Verlag, Berlin, Heidelberg, 2006.
(Available online at: https://github.com/Benlau93/Bishop-Pattern-Recognition-and-Machine-Learning-2006)
I. Goodfellow, Y. Bengio, and A. Courville. Deep Learning. MIT Press, 2016.
(Available online at: https://www.deeplearningbook.org)
Christopher M. Bishop and Hugh Bishop. Deep Learning: Foundations and Concepts. Springer, 2024.
(Provides an up-to-date introduction to the foundations of deep learning.)
Kevin P. Murphy. Machine Learning: A Probabilistic Perspective. MIT Press, 2012.
(An advanced reference on probabilistic approaches to machine learning.)
Richard S. Sutton and Andrew G. Barto. Reinforcement Learning: An Introduction. Second Edition. MIT Press, 2018.
(Available free of charge at: http://incompleteideas.net/book/the-book-2nd.html)
Aurélien Géron. Hands-On Machine Learning with Scikit-Learn, Keras & TensorFlow. Third Edition. O'Reilly Media, 2022.
(A practical guide to implementing machine learning algorithms in Python.)
Melanie Mitchell. Artificial Intelligence: A Guide for Thinking Humans. Farrar, Straus and Giroux, 2019.
(An accessible introduction to the foundations, limitations, and challenges of artificial intelligence.)
Virginia Dignum. Responsible Artificial Intelligence: How to Develop and Use AI in a Responsible Way. Springer, 2019.
(An introduction to the ethical, societal, and legal aspects of artificial intelligence.)
MIT OpenCourseWare. Artificial Intelligence and Machine Learning course materials.
Stanford University – CS229: Machine Learning. Course materials and lecture notes.
Elements of AI. A free online introductory course on artificial intelligence developed by the University of Helsinki.
Software
For Python programming, the latest version of the Anaconda distribution, which includes Python 3.x and the Spyder integrated development environment (https://www.anaconda.com/products/individual), will be used. Alternatively, any development environment compatible with Python 3.x may be used, such as Visual Studio Code, PyCharm Community Edition, or JupyterLab.
Course groups and languages
The information provided is provisional until November 30. After this date, you will be able to consult the language of each group through this link. To access the information, you will need to enter the course CODE
| Type of teaching | Group | Language | Semester | Shift |
|---|---|---|---|---|
| (TE) Theory | 11 | Catalan | first semester | afternoon |
| (PAUL) Classroom practices | 11 | Catalan | first semester | afternoon |
| (PLAB) Practical laboratories | 32 | Catalan | first semester | afternoon |