Does removing pooling layers from convolutional neural networks improve results?

CFG Santos, TP Moreira, D Colombo, JP Papa - SN Computer Science, 2020 - Springer
Due to their number of parameters, convolutional neural networks are known to take long
training periods and extended inference time. Learning may take so much computational …

Avoiding overfiting: new algorithms to improve generalisation in convolutional neural networks

CFG Santos - 2022 - repositorio.ufscar.br
Deep Learning has achieved state-of-the-art results in several domains, such as image
processing, natural language processing, and audio processing. To accomplish such …

Efficient Brazilian Sign Language Recognition: A Study on Mobile Devices

VL Fabris, F de Castro Bastos, ACAM de Faria… - … Congress on Pattern …, 2023 - Springer
Abstract Automatic Sign Language Recognition (SLR) is a critical step in facilitating
communication between deaf and hearing people. An interesting application of such a …

Theoretical background and related works

LCS Afonso, AX Falcão, JP Papa - Optimum-Path Forest, 2022 - Elsevier
Abstract The Optimum-Path Forest (OPF) is a framework for the design of graph-based
classifiers, which covers supervised, semisupervised, and unsupervised applications. The …