Artificial Intelligence

Year
0
Academic year
2023-2024
Code
02000031
Subject Area
Intelligent Systems
Language of Instruction
Portuguese
Other Languages of Instruction
English
Mode of Delivery
Face-to-face
Duration
SEMESTRIAL
ECTS Credits
6.0
Type
Compulsory
Level
2nd Cycle Studies - Mestrado

Recommended Prerequisites

Programming competences. Introductory course on Artificial Intelligence (recommended).

Teaching Methods

A Project Based Learning approach is adopted, directed towards competence acquisition through the development of a laboratory work (project) with a high research component, demanding the combination of theoretical concepts and promotes critical reasoning over complex problems. The work comprises the writing of a scientific article, describing the work done, as well as its presentation and defense.

Theoretical classes comprise detailed presentation of Artificial Intelligence concepts, principles and fundamental theories.

Learning Outcomes

To provide the students with advanced concepts, principles and theories required for building real world applications with agents or systems that can reason, behave or interact with their environment in an intelligent way by learning and reasoning about the real world.

Acquiring competencies in synthesis and analysis, organization and planning, written communication, problem solving, decision-making, team work, critical reasoning, autonomous learning, practical application of theoretical knowledge, and research.

Work Placement(s)

No

Syllabus

1. Autonomous Agents and Multi-Agent Systems

1.1 Agents and environments

1.2 Taxonomy of agents

1.3 BDI Architecture

1.4 Logic for Knowledge Representation and Reasoning

1.5 Agent-oriented software engineering

1.6 Agent communication

1.7 Establishing agreements: negotiation and argumentation

1.8 Working together: cooperation and coordination

2. Knowledge and Reasoning with Uncertainty

2.1 Quantification of uncertainty

2.2 Probabilistic reasoning

2.3 Probabilistic reasoning over time

2.4 Decision-making and action: single and sequential decisions

3. Symbolic Learning

3.1 Example-based version space learning

3.2 Explanation-based learning

3.3 Inductive Logic Programming

3.4 Instance-based Learning

3.5 Bayesian learning; learning Bayesian Networks

4 Reinforcement Learning

4.1 Passive and Active Reinforcement Learning

4.2 Exploration vs. Exploitation

4.3 Generalization

4.4 Policy search

5. Applications

6. Philosophical and Ethical Issues.

Head Lecturer(s)

Luís Miguel Machado Lopes Macedo

Assessment Methods

Assessment
Exam: 40.0%
Laboratory work or Field work: 60.0%

Bibliography

- Russell, S. and Norvig, P. Artificial Intelligence: a Modern Approach, 3rd. Edition, Prentice Hall, 2010.

- Wooldridge, M.. An introduction to MultiAgent Systems, 2nd. Edition, John Wiley, 2009.

- Shoham, Y. and Leyton-Brown, K. Multiagent Systems – Algorithmic game-theoretic and logical foundations. Cambridge University Press, 2009.

- Jannach, D., Zanker, M., Felfernig, A., and Friedrich, G. Recommender Systems: An Introduction. Cambridge University Press, 2010.

- Settles, B. Active Learning. Morgan & Claypool Publishers, 2012.