6 ECTS; 2º Ano, 2º Semestre, 42,0 PL + 28,0 TP + 5,0 OT , Cód. 814345.
Lecturer
- Renato Eduardo Silva Panda (1)(2)
(1) Docente Responsável
(2) Docente que lecciona
Prerequisites
Basic programming skills and introductory knowledge of algorithms and data structures.
Objectives
This course introduces the fundamental concepts of Artificial Intelligence, providing an overview of its main approaches, methods, and application domains.
Students are expected to develop the ability to model problems, apply basic solution techniques, and understand the role of machine learning in intelligent systems, supporting further advanced courses in the field.
By the end of the course, students should be able to:
Understand core AI concepts and historical evolution
Model problems in terms of perception, decision, and action
Apply basic search and problem-solving techniques
Understand knowledge representation and reasoning principles
Use elementary machine learning techniques
Interpret results and recognize limitations
Program
1. Introduction to AI: concepts, history, applications
2. Intelligent agents: perception, action, environments, rationality
3. Problem solving: uninformed and informed search, heuristics, games
4. Knowledge representation and reasoning: propositional and predicate logic, planning
5. Machine learning: classification, regression, decision trees, k-NN, neural networks, model evaluation
6. Nature-inspired techniques: genetic algorithms
All topics above are supported with practical implementation: tools and result analysis.
Evaluation Methodology
Assessment consists of two components:
Written exam (50%)
Individual assessment covering theoretical concepts.
Practical work (50%)
Laboratory assignments applying AI techniques.
A minimum of 35% in each component is required. Final grade is the weighted average (020 scale), with a minimum of 10 for approval.
Bibliography
(2014). Introduction to Machine Learning. 3rd ed.. Cambridge, MA: MIT Press
(2020). Artificial Intelligence: A Modern Approach. 4th ed.. Harlow: Pearson Education Limited
Teaching Method
Lectures for core concepts and lab sessions for exercises and development of practical applications using Artificial Intelligence tools.
Software used in class
Python, Anaconda, Jupyter Notebook, Scikit-learn, Weka
