no code implementations • 20 Dec 2023 • José Guilherme de Almeida, Nuno M. Rodrigues, Sara Silva, Nickolas Papanikolaou
Deep learning models trained with large amounts of data have become a recent and effective approach to predictive problem solving -- these have become known as "foundation models" as they can be used as fundamental tools for other applications.
1 code implementation • 7 Aug 2023 • Rita T. Sousa, Sara Silva, Heiko Paulheim, Catia Pesquita
Explicitly considering negative statements has been shown to improve performance on tasks such as entity summarization and question answering or domain-specific tasks such as protein function prediction.
no code implementations • 21 Jul 2023 • Rita T. Sousa, Sara Silva, Catia Pesquita
We also generate knowledge graph embeddings for each dataset with two popular path-based methods and evaluate the performance in each task.
1 code implementation • 22 Jun 2023 • Rita T. Sousa, Sara Silva, Catia Pesquita
We propose SEEK, a novel approach for explainable representations to support relation prediction in knowledge graphs.
no code implementations • 8 Feb 2021 • Nuno M. Rodrigues, João E. Batista, Leonardo Trujillo, Bernardo Duarte, Mario Giacobini, Leonardo Vanneschi, Sara Silva
We present a novel approach for time series classification where we represent time series data as plot images and feed them to a simple CNN, outperforming several state-of-the-art methods.
1 code implementation • 31 Jan 2020 • João E. Batista, Sara Silva
One problem found when working with satellite images is the radiometric variations across the image and different images.
no code implementations • 30 Jan 2020 • Nuno M. Rodrigues, Sara Silva, Leonardo Vanneschi
Fitness landscapes are a useful concept to study the dynamics of meta-heuristics.
1 code implementation • 21 Jan 2020 • Nuno M. Rodrigues, João E. Batista, Sara Silva
Ensemble learning is a powerful paradigm that has been usedin the top state-of-the-art machine learning methods like Random Forestsand XGBoost.
no code implementations • 19 Jun 2017 • Ivo Gonçalves, Sara Silva, Carlos M. Fonseca, Mauro Castelli
The usage of the proposed semantic stopping criteria in conjunction with the computation of optimal mutation/learning steps also results in small trees and neural networks.