Computational Intelligence

Base Knowledge

Approved in the following curricular units:

– Análise Matemática I and II;

– Programação Orientada a Objetos;

– Introdução à Inteligência Artificial;

– Conhecimento e Raciocínio.

Teaching Methodologies

The course consists of lectures and practical sessions. The lectures present methodologies and examples of applications to case studies. The practical classes focus on the practical implementation of algorithms and the supervision of the completion of a project and research seminar.

Students are assessed on the basis of two components, theoretical (10 marks) and practical (10 marks).

The theoretical component is assessed by a written examination.

The practical component is assessed through two practical assignments and a research seminar:

– Practical Work I – Identifying a problem and solving it using neural networks (2 marks);

– Practical Work II – Developing an application using Evolutionary Computation techniques (5 marks);

– Seminar – Research work (3 marks).

Learning Results

This curriculum unit studies advanced concepts in computational intelligence, essentially learning mechanisms with neural networks, neurodiffuse systems, evolutionary computing paradigms, deep learning and reinforcement learning.

The main objectives are:

– Acquire knowledge in the field of Computational Intelligence;

– Apply computational intelligence techniques to real cases;

– Understand and apply advanced learning techniques;

– Knowledge and application of complex problem solving algorithms.

 

The main competences to be acquired are:

– Knowledge of the main computational intelligence paradigms;

– Analyse a problem, identify its characteristics and solution strategies;

– Recognise the advantages and limitations of using problem solving algorithms;

– Promote the autonomous development of new advanced problem-solving strategies.

Program

1 Introduction to Computational Intelligence:

– Overview, Methodologies and Applications;

– Analysing real problems;

– Learning mechanisms.

2. Machine Learning.

3. Evolutionary Computation and Collective Intelligence paradigms:

– Particle Swarm Intelligence (PSO) and Variants;

– Ant Colony Optimisation.

4. Advanced Topics in Neuro-Diffuse Systems.

5. Deep-Learning.

6. Reinforcement Learning.

Curricular Unit Teachers

Internship(s)

NAO

Bibliography

Main:

– Müller, A. C., & Guido, S. (2016). Introduction to machine learning with Python: a guide for data scientists. ” O’Reilly Media, Inc.”. 1A-4-197 (ISEC) – 18236

 

Complementary:

– Géron, A. (2019). Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and techniques to build intelligent systems. ” O’Reilly Media, Inc.”.

– Shah, C. (2022). A hands-on introduction to machine learning. Cambridge University Press.

– Engelbrecht, A. P. (2007). Computational intelligence: an introduction. John Wiley & Sons. 1A-4-182 (ISEC) – 16371

– Panigrahi, B. K., Shi, Y., & Lim, M. H. (Eds.). (2011). Handbook of swarm intelligence: concepts, principles and applications (Vol. 8). Springer Science & Business Media.

– Haykin, S., & Network, N. (2004). A comprehensive foundation. Neural networks2(2004), 41