ISLA IPGT 2129

Artificial Intelligence

• ApresentaçãoPresentation

  The Artificial Intelligence Course Module aims to provide students with an integrated overview of the key concepts, methods and applications of AI. The module will cover the fundamentals of Artificial Intelligence, its relationship with Data Science and Machine Learning, the main types of machine learning, and the implementation of algorithms in Python. The module also covers deep learning, computer vision, natural language processing, LLMs, generative AI, prompt engineering and RAG. The differences between chatbots, virtual assistants and intelligent agents will also be analysed, as well as topics relating to explainability, security, privacy, ethics and the responsible use of AI.  
• ProgramaProgramme

  Introduction to AI: evolution, benefits, limitations, applications and problems addressed. 2. AI in Data Science: relationship between AI, data, machine learning, knowledge and decision-making. 3. AI technologies: data preparation, cloud, Python, libraries, frameworks, APIs and development environments. 4. Machine Learning: problem definition, data exploration and preparation, training, validation, testing, evaluation and CRISP-DM. 5. Types of ML: supervised, unsupervised, semi-supervised and reinforcement learning. 6. Algorithms: regression, classification, Random Forest, nearest neighbours, SVM, ensembles, clustering, dimensionality reduction, association and anomaly detection. 7. Python implementation: metrics, cross-validation, hyperparameters, overfitting and explainability. 8. Deep Learning and generative AI: neural networks, vision, NLP, transformers, LLMs, prompting and RAG. 9. Chats, assistants, agents and responsible AI: memory, planning, security, ethics and governance.
• ObjectivosObjectives

  By the end of the module, students should be able to understand the fundamentals, benefits, limitations and main challenges of Artificial Intelligence (AI), relating it to Data Science and to the technologies, data and resources that underpin its operation. They should understand the machine learning process and distinguish between supervised, unsupervised and reinforcement learning; select, implement, evaluate and compare, in Python, algorithms for regression, classification, clustering, dimensionality reduction and anomaly detection; understand the fundamentals of deep learning and its applications in computer vision, NLP, LLM and generative AI; distinguish between chatbots, virtual assistants and intelligent agents; and develop, document, present and defend a functional AI solution, taking into account quality, explainability, security, ethics and legal compliance.  
• BibliografiaBibliography

  Russell, S. J., & Norvig, P. (2021). Artificial intelligence: A modern approach (4th ed.). Pearson. Géron, A. (2022). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems (3rd ed.). O'Reilly Media. Chollet, F. (2025). Deep learning with Python (3rd ed.). Manning Publications. Sutton, R. S., & Barto, A. G. (2018). Reinforcement learning: An introduction (2nd ed.). MIT Press. Jurafsky, D., & Martin, J. H. (2026). Speech and language processing: An introduction to natural language processing, computational linguistics, and speech recognition (3rd ed., online manuscript). https://web.stanford.edu/~jurafsky/slp3/  
• MetodologiaMethodology

  Methodologies such as Project-Based Learning, Problem-Based Learning, Flipped Classroom, Learning by Doing, Challenge-Based Learning, Live Coding, interactive Jupyter/Colab labs, Peer Learning, gamification and AI-assisted learning may be used. These approaches promote experimentation, Python programming, problem-solving, critical thinking, autonomy, collaboration and the practical application of Artificial Intelligence concepts.
• LínguaLanguage

  Português
• TipoType

  Semestral
• ECTS

  6
• NaturezaNature

  Mandatory
• EstágioInternship

  Não
• AvaliaçãoEvaluation

  Descrição dos instrumentos de avaliação (individuais e de grupo)  - testes, trabalhos práticos, relatórios, projetos... respetivas datas de entrega/apresentação... e ponderação na nota final.

   

  Descrição	Data limite	Ponderação
  Prova de avaliação	13-01-2027	60%
  Trabalho prático de avaliação (individual)	06-01-2027	30%
  Assiduídade e participação (minimo de 70% de presenças)	-----	10%

   

  Avaliação Especial

  Os estudantes a quem tenha sido reconhecido estatuto especial, nos termos do Regulamento Geral de Avaliação - incluindo trabalhador-estudante, dirigente associativo, atleta de alta competição, atleta em representação da instituição no desporto universitário, atleta federado, membro das forças de segurança, militar, estudante com necessidades educativas especiais e outros legalmente previstos - podem requerer, mediante pedido devidamente fundamentado dirigido ao Diretor do Ciclo de Estudos, a aplicação do regime especial de avaliação previsto no artigo 6.º.