840 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Universidade Federal Rural de PernambucoBR89 papers
- Universidade Federal da ParaíbaBR67 papers
- Universidade Federal de AlagoasBR44 papers
- Universidade Federal de Santa MariaBR41 papers
- Universidade de São PauloBR37 papers
- Centre National de la Recherche ScientifiqueFR34 papers
- University of CalgaryCA31 papers
- Universidade de PernambucoBR26 papers
- University of AkronUS21 papers
- Universidade Federal do Rio Grande do NorteBR19 papers
- École de Technologie SupérieureCA17 papers
- Universidade Estadual de Campinas (UNICAMP)BR17 papers
6 papers · 2 filters
Label noise detection under the Noise at Random model with ensemble filters
Kecia G. Moura, Ricardo B. C. Prudêncio, George D. C. Cavalcanti
Label noise detection has been widely studied in Machine Learning because of its importance in improving training data quality. Satisfactory noise detection has been achieved by ad…
Transportation Scenario Planning with Graph Neural Networks
Ana Alice Peregrino, Soham Pradhan, Zhicheng Liu +2
Providing efficient human mobility services and infrastructure is one of the major concerns of most mid-sized to large cities around the world. A proper understanding of the dynami…
Data vs classifiers, who wins?
Lucas F. F. Cardoso, Vitor C. A. Santos, Regiane S. Kawasaki Francês +2
The experiments covered by Machine Learning (ML) must consider two important aspects to assess the performance of a model: datasets and algorithms. Robust benchmarks are needed to…
Distance Metric Learning through Minimization of the Free Energy
Dusan Stosic, Darko Stosic, Teresa B. Ludermir +1
Distance metric learning has attracted a lot of interest for solving machine learning and pattern recognition problems over the last decades. In this work we present a simple appro…
Enhanced Isotropy Maximization Loss: Seamless and High-Performance Out-of-Distribution Detection Simply Replacing the SoftMax Loss
David Macêdo, Teresa Ludermir
Current out-of-distribution detection approaches usually present special requirements (e.g., collecting outlier data and hyperparameter validation) and produce side effects (e.g.,…
Training Aware Sigmoidal Optimizer
David Macêdo, Pedro Dreyer, Teresa Ludermir +1
Proper optimization of deep neural networks is an open research question since an optimal procedure to change the learning rate throughout training is still unknown. Manually defin…