5 papers
Benford's Law as a Distributional Prior for Post-Training Quantization of Large Language Models
Arthur Negrão, Pedro Silva, Vander L. S. Freitas +2
Post-training quantization (PTQ) is a practical way to reduce the memory footprint of large language models, but low-bit quantization is sensitive to mismatches between the quantiz…
PD-Loss: Proxy-Decidability for Efficient Metric Learning
Pedro Silva, Guilherme A. L. Silva, Pablo Coelho +4
Deep Metric Learning (DML) aims to learn embedding functions that map semantically similar inputs to proximate points in a metric space while separating dissimilar ones. Existing m…
Leveraging graph neural networks and mobility data for COVID-19 forecasting
Fernando H. O. Duarte, Gladston J. P. Moreira, Eduardo J. S. Luz +2
The COVID-19 pandemic has claimed millions of lives, spurring the development of diverse forecasting models. In this context, the true utility of complex spatio-temporal architectu…
Leveraging Visibility Graphs for Enhanced Arrhythmia Classification with Graph Convolutional Networks
Rafael F. Oliveira, Gladston J. P. Moreira, Vander L. S. Freitas +1
Arrhythmias, detectable through electrocardiograms (ECGs), pose significant health risks, underscoring the need for accurate and efficient automated detection techniques. While rec…
A Decidability-Based Loss Function
Pedro Silva, Gladston Moreira, Vander Freitas +3
Nowadays, deep learning is the standard approach for a wide range of problems, including biometrics, such as face recognition and speech recognition, etc. Biometric problems often…