Sistemas Inteligentes

Objectives

To train students in the fundamentals of the theory of intelligent systems. Provide the basic principles of fuzzy logic (fuzzy) and its application to modelling, control and qualitative decision. Introduction to modelling and control by neural networks and to the theory underlying the neuro-fuzzy systems, fuzzy optimization and deep learning applied to neural networks and fuzzy modelling.

Syllabus

Introduction to soft computing. Fuzzy sets. Fuzzy operations, fuzzy relations and compositional rule of inference. Fuzzy systems. Rule based fuzzy models: linguistic (Mamdani) and Takagi-Sugeno. Dynamic systems identification using fuzzy clustering. Interpretability of fuzzy models. Artificial neural networks: definitions, basic architectures and learning. Multi-layer perceptron. Radial basis function networks. Recurrent networks. Dynamic modelling using neural networks. Neuro-fuzzy systems: synergies of the combination of the two modelling methodologies. Deep learning. Classic fuzzy control. Model-based control. Predictive control. Linear and nonlinear internal model control. Inverse fuzzy control. Control with fuzzy objective function. Formulation from the perspective of fuzzy decision theory. Branch- and-bound algorithm for predictive control. Fuzzy predictive filters. Control with neural networks. Applications to decision and control problems in engineering.

Cross Competence Component

Project done in group requires critical and inovative reasoning, decision making, team work, leadership, oral communication skills, use of computer multimedia tools (20% of the evaluation component of the project).

Laboratorial Component

1 - Fuzzy sets, Fuzzy relations and Fuzzy Systems. 2 - Fuzzy Control. 3 - Fuzzy Modeling and Neural Modeling. 4 - Deep Learning.

Programming And Computing Component

Programming with Matlab/Simulink. Use of Python, Java, C++ or other programmming languages, if needed.

Ethical Principles

All members of a group are responsible for the group’s work In any assessment, every student shall honestly disclose any help received and sources used. In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.