IPLUSO 2129

Artificial Intelligence

• ApresentaçãoPresentation

  The Artificial Intelligence course unit is offered in the 3rd year of the Bachelor’s degree in Automation and Computer Systems and aims to provide a structured and rigorous introduction to the fundamental principles, models, and techniques of Artificial Intelligence (AI). The course covers the main AI paradigms, with particular emphasis on machine learning, reinforcement learning, and their practical application in engineering and computational systems. The scope of the course includes both theoretical and practical components, enabling students to understand the conceptual foundations of AI, its application domains, and inherent limitations, while also developing skills in the implementation of algorithms and models in a computational environment. The course promotes a critical and applied perspective, preparing students to integrate AI-based solutions into automation systems, networks, intelligent systems, and industrial and technological applications.
• ProgramaProgramme

  The course covers the fundamentals of Artificial Intelligence, starting with core concepts, terminology, and historical background, as well as the relationship between AI, machine learning, and deep learning. Intelligent agents, knowledge representation, and problem-solving techniques are introduced. The main learning paradigms are studied, including supervised, unsupervised, and reinforcement learning, addressing datasets, training, validation, and performance metrics. Classical classification and regression models, clustering techniques, and introductory artificial neural networks are explored. The course also includes reinforcement learning and practical examples applied to automation and computing systems. Finally, limitations, risks, and ethical aspects related to the use of AI systems are discussed.
• ObjectivosObjectives

  By the end of the course, students should be able to: (i) explain core AI, ML, DL and RL concepts; (ii) formulate problems and select suitable models/algorithms; (iii) implement, train and evaluate models in Python using appropriate metrics and validation; (iv) interpret results and recognise data requirements, bias and limitations; (v) integrate AI solutions in automation and computing scenarios while respecting ethical and scientific good practices
• BibliografiaBibliography

  Russell, S. J., & Norvig, P. (2021). Artificial intelligence: A modern approach (4th ed.). Pearson Education. Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O’Reilly Media. Mitchell, T. M. (1997). Machine learning. McGraw-Hill. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press.  
• MetodologiaMethodology

  The course adopts active, student-centred methodologies, combining theoretical-practical classes with guided problem solving and small project development. Practical examples and Python scripts are used to illustrate AI concepts and promote learning through experimentation. Critical analysis of results, classroom discussion, and guided exercises foster autonomous reasoning. The use of up-to-date computational tools and real or synthetic datasets brings the teaching and learning process closer to professional contexts, promoting technical, analytical, and critical thinking skills.
• LínguaLanguage

  Português
• TipoType

  Semestral
• ECTS

  5
• NaturezaNature

  Mandatory
• EstágioInternship

  Não