Propostas Submetidos

DEI - FCTUC
Gerado a 2024-11-21 22:00:25 (Europe/Lisbon).
Voltar

Titulo Estágio

Automatic Design of Representations

Áreas de especialidade

Sistemas Inteligentes

Engenharia de Software

Local do Estágio

CISUC

Enquadramento

Evolutionary Algorithms (EAs) are computational methods loosely inspired by natural selection and genetics principles. Each iteration is typically composed of three steps: selection of the most promising individuals, creation of a new set of solutions by means of variation operators and definition of survivors.

Despite these simple processing rules, EAs are robust search procedures able to quickly identify good-quality solutions. However, in many situations, the effectiveness of EAs can be greatly enhanced if the representation of the solutions is adjusted to the specific situation being addressed. Usually, the definition of a specific representation is a laborious task, usually performed through a trial and error process and requiring domain expertise.

Objetivo

The main goal of this work is to design, implement and validate an approach to automatically design representations for evolutionary algorithms. In concrete, we will explore the automatic design of embeddings that are going to be used to map solutions between different search spaces.

Plano de Trabalhos - Semestre 1

1 - Review of the literature.
2 - Framework Proposal
3 - Preliminary Implementation
4 - Writing of the intermediate report

Plano de Trabalhos - Semestre 2

5 - Analysis of the results
6 - Framework Refinement
7 - Validation of the results
8 - Scientific Article with the main results
9 - Writing of the thesis

Condições

The work is to be conducted at the ECOS and CMS groups of CISUC. A workplace will be provided as well as the required computational resources.
There is a possibility of the student being awarded a scholarship (Bolsa de Investigação para Licenciado) for at least 6 months. The scholarship will follow the Fundação para a Ciência e Tecnologia (FCT) monthly stipend guidelines.

Orientador

Penousal Machado / Nuno Lourenço
machado@dei.uc.pt 📩