ISLA Santarém 2129

Artificial Intelligence

• ApresentaçãoPresentation

  This module is an introduction to the basic concepts and techniques of Artificial Intelligence, with three main areas of activity. First, the formalization of what a machine is, both from the perspective of symbol manipulation in the Turing machine, and in the McCulloch and Pitts machines that work with patterns of interconnection between nodes in neuron networks. Second, the concept of rational agent in AI, which emerges from the intersection with cognitive sciences, and the various implementations of structured exhaustive search algorithms (informed and uninformed). Still within this area of ¿¿focus, the concepts of stochastic search and constraint satisfaction algorithms (CSPs) are introduced. Finally, in the third focus area, students learn the basics and uses of some of the advanced artificial intelligence algorithms that are used today.
• ProgramaProgramme

  1. Introduction to Artificial Intelligence: Definition and history of AI. Applications and impacts of AI on society. 2. Intelligent Agents: Agents and environments. Simple reactive agents. Goal-based agents. 3. Problem Solving: Problem formulation. Uninformed search strategies. Informed search strategies. 4. Propositional and First Order Logic: Representation of knowledge using logic. Logical inference. Problem solving using logic. 5. Machine Learning: Introduction to supervised and unsupervised learning. Machine learning algorithms. 6. Ethics and Social Implications of AI.
• ObjectivosObjectives

  Objectives: O1. Present the fundamental concepts about AI. O2. Transmit solid basic knowledge about the area of artificial intelligence in terms of fundamentals, techniques, and practical application. Competences: C1. Identify problems that can be solved with Artificial Intelligence. C2. Represent knowledge with computational structures. C3. Understand and apply the main algorithms for solving problems. C4. Understand the problems associated with Machine Learning and use the most appropriate resolution techniques.
• BibliografiaBibliography

  Aggarwal, C. C. (2021). Artificial Intelligence A Textbook. Springer. Chopra, D., & Khurana, R. (2023). Introduction to Machine Learning with Python. Bentham Science Publishers. Kaplan, J. (2024). Generative Artificial Intelligence: What Everyone Needs to Know. Oxford University Press. Poole, D. L., & Mackworth, A. K. (2024). Python code for Artificial Intelligence. eBook. URL: https://artint.info/AIPython/ Teik Toe Teoh, Zheng Rong (2022). Artificial Intelligence with Python. Springer.
• MetodologiaMethodology

  Face-to-face 1. Expository method: presentation of each of the content topics.  2. Practical application through guided exercises to consolidate knowledge.  3. Laboratory practice: based on the Problem-Based Learning (PBL) methodology, aiming to find solutions to problems identified by students or proposed by the teacher.  Independent: 4. Guided research proposed by the teacher. The teacher provides feedback on the development of the problem addressed in the laboratory practice in person in the classroom and/or through the Moodle teaching/learning support platform.
• LínguaLanguage

  Português
• TipoType

  Semestral
• ECTS

  5
• NaturezaNature

  Mandatory
• EstágioInternship

  Não
• AvaliaçãoEvaluation

  Avaliação Curricular (contínua):

  - A1. Trabalho prático (grupo).

  - A2. Teste final teórico-prático (individual).

  A classificação final é calculada através da fórmula Classificação Final = A1*0,6+A2*0,4.

  O estudante é aprovado se obtiver classificação igual ou superior a 9,5 valores.

  Avaliação Final e/ou de Recurso/Especial:

  Hipótese 1:

  - A1. Trabalho prático (grupo). O estudante participou no trabalho de grupo o qual obteve classificação positiva e obteve classificação positiva na componente individual: mantém a classificação que será considerada nas épocas subsequentes (Avaliação Final, Recurso/Especial)

  - A2. Teste final teórico/prático (individual). O estudante realiza este Teste em qualquer das épocas em que se submeta a avaliação.

  A classificação final é calculada através da fórmula prevista na avaliação Curricular (contínua).

  Hipótese 2:

  - A1. Trabalho prático (grupo). O estudante não participou no trabalho de grupo, ou participando obteve classificação negativa no trabalho ou na componente de avaliação individual. Nestas circunstâncias esta componente da avaliação não poderá ser utilizada na Avaliação Final, Avaliação em Época de Recurso/Especial.

  O estudante realiza o exame teórico-prático (A=100%) e é aprovado se obtiver uma classificação igual ou superior a 9,5 valores em 20.