GI-LIDIA - Artigos: Envíos recentes
Mostrando ítems 36-40 de 63
-
Wavefront Marching Methods: A Unified Algorithm to Solve Eikonal and Static Hamilton-Jacobi Equations
(IEEE, 2019-12)[Abstract]: This paper presents a unified propagation method for dealing with both the classic Eikonal equation, where the motion direction does not affect the propagation, and the more general static Hamilton-Jacobi ... -
E2E-FS: An End-to-End Feature Selection Method for Neural Networks
(IEEE, 2023-07)[Abstract]: Classic embedded feature selection algorithms are often divided in two large groups: tree-based algorithms and LASSO variants. Both approaches are focused in different aspects: while the tree-based algorithms ... -
Fast anomaly detection with locality-sensitive hashing and hyperparameter autotuning
(Elsevier, 2022-08)[Abstract]: This paper presents LSHAD, an anomaly detection (AD) method based on Locality Sensitive Hashing (LSH), capable of dealing with large-scale datasets. The resulting algorithm is highly parallelizable and its ... -
Fast deep autoencoder for federated learning
(Elsevier Ltd, 2023-11)[Abstract]: This paper presents a novel, fast and privacy preserving implementation of deep autoencoders. DAEF (Deep AutoEncoder for Federated learning), unlike traditional neural networks, trains a deep autoencoder network ... -
FedHEONN: Federated and homomorphically encrypted learning method for one-layer neural networks
(Elsevier B.V., 2023)[Abstract]: Federated learning (FL) is a distributed approach to developing collaborative learning models from decentralized data. This is relevant to many real applications, such as in the field of the Internet of Things, ...