activity
20192021
most citedTraining Aware Sigmoidal Optimizer

1 citations · 1 across the 1 of their papers we have counts for

collaborators
Showing 2019Show all

5 papers · 1 filter

eess.AS2019

Additive Margin SincNet for Speaker Recognition

João Antônio Chagas Nunes, David Macêdo, Cleber Zanchettin

Speaker Recognition is a challenging task with essential applications such as authentication, automation, and security. The SincNet is a new deep learning based model which has pro…

cs.LG2019

Heartbeat Anomaly Detection using Adversarial Oversampling

Jefferson L. P. Lima, David Macêdo, Cleber Zanchettin

Cardiovascular diseases are one of the most common causes of death in the world. Prevention, knowledge of previous cases in the family, and early detection is the best strategy to…

cs.LG2019

Squeezed Very Deep Convolutional Neural Networks for Text Classification

Andréa B. Duque, Luã Lázaro J. Santos, David Macêdo +1

Most of the research in convolutional neural networks has focused on increasing network depth to improve accuracy, resulting in a massive number of parameters which restricts the t…

cs.LG2019

Spatial-Temporal Graph Convolutional Networks for Sign Language Recognition

Cleison Correia de Amorim, David Macêdo, Cleber Zanchettin

The recognition of sign language is a challenging task with an important role in society to facilitate the communication of deaf persons. We propose a new approach of Spatial-Tempo…

cs.CL2019

Hierarchical Attentional Hybrid Neural Networks for Document Classification

Jader Abreu, Luis Fred, David Macêdo +1

Document classification is a challenging task with important applications. The deep learning approaches to the problem have gained much attention recently. Despite the progress, th…