| Texto completo | |
| Autor(es): |
Napoli, Otavio Oliveira
;
de Almeida, Ana Maria
;
Borin, Edson
;
Breternitz Jr, Mauricio
Número total de Autores: 4
|
| Tipo de documento: | Artigo Científico |
| Fonte: | Neurocomputing; v. 610, p. 12-pg., 2024-09-05. |
| Resumo | |
Weightless Neural Networks (WNN) are ideal for Federated Learning due to their robustness and computational efficiency. These scenarios require models with a small memory footprint and the ability to aggregate knowledge from multiple models. In this work, we demonstrate the effectiveness of using Bloom filter variations to implement DRASiW models-an adaptation of WNN that records both the presence and frequency of patterns-with minimized memory usage. Across various datasets, DRASiW models show competitive performance compared to models like Random Forest, k-Nearest Neighbors, Multi-layer Perceptron, and Support Vector Machines, with an acceptable space trade-off. Furthermore, our findings indicate that Bloom filter variations, such as Count Min Sketch, can reduce the memory footprint of DRASiW models by up to 27% while maintaining performance and enabling distributed and federated learning strategies. (AU) | |
| Processo FAPESP: | 13/08293-7 - CECC - Centro de Engenharia e Ciências Computacionais |
| Beneficiário: | Munir Salomao Skaf |
| Modalidade de apoio: | Auxílio à Pesquisa - Centros de Pesquisa, Inovação e Difusão - CEPIDs |