Titulo Estágio
Automatic Design of Autoencoders using NeuroEvolution
Áreas de especialidade
Sistemas Inteligentes
Engenharia de Software
Local do Estágio
CISUC
Enquadramento
Dealing with the learning and extraction of knowledge has become increasingly challenging due to the continuously growing volume of data with datasets often consisting of thousands or even millions of instances. Consequently, it is crucial to develop methods that can efficiently convert information into a usable format for learning models within a reasonable timeframe. Moreover, feature compression approaches also serve as a valuable solution in response to the demand for real-time data processing.
AutoEncoders (AEs) are ANN models that can be used to reduce the data dimensionality. However, to build these models, practitioners often follow an iterative trial-and-error process, to select and tune the topology and learning parameters. Over the years, various methods seeking to automate this laborious task have been proposed, with Evolutionary Algorithms (EAs) obtaining impressive results.
Objetivo
The main goal of this work is to design, implement and validate an approach to automatically design AutoEncoders using Evolutionary Algorithms.
Plano de Trabalhos - Semestre 1
1 - Literature Review;
2 - Framework Selection/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
Nuno Lourenço / Penousal Machado
naml@dei.uc.pt 📩