Search Results for author: Joao Paulo Schwarz Schuler

Found 6 papers, 6 papers with code

Grouped Pointwise Convolutions Significantly Reduces Parameters in EfficientNet

1 code implementation 23rd International Conference of the Catalan Association for Artificial Intelligence 2021 Joao Paulo Schwarz Schuler, Santiago Romani, Mohamed Abdel-Nasser, Hatem Rashwan, Domenec Puig

Our proposal is to improve the pointwise (1x1) convolutions, whose number of parameters rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer.

Image Classification

Grouped Pointwise Convolutions Reduce Parameters in Convolutional Neural Networks

2 code implementations Mendel 2022 Joao Paulo Schwarz Schuler, Santiago Romani, Mohamed Abdel-Nasser, Hatem Rashwan, Domenec Puig

In Deep Convolutional Neural Networks (DCNNs), the parameter count in pointwise convolutions quickly grows due to the multiplication of the filters and input channels from the preceding layer.

Spam detection

Saving 77% of the Parameters in Large Language Models Technical Report

1 code implementation researchgate.net 2025 Joao Paulo Schwarz Schuler, Alejandra Rojas-Gómez

This technical report demonstrates that large language models (LLMs) can maintain their learning capacity while reducing their non-embedding parameters by up to 77%.

4k Text Generation

Cannot find the paper you are looking for? You can Submit a new open access paper.