On the Impact of Sampling on Deep Sequential State Estimation

no code implementations • 28 Nov 2023 • Helena Calatrava, Ricardo Augusto Borsoi, Tales Imbiriba, Pau Closas

In this paper, importance sampling is applied to the DKF framework for learning deep Markov models, resulting in the IW-DKF, which shows an improvement in terms of log-likelihood estimates and KL divergence between the variational distribution and the transition model.

Jammer classification with Federated Learning

no code implementations • 5 Jun 2023 • Peng Wu, Helena Calatrava, Tales Imbiriba, Pau Closas

Jamming signals can jeopardize the operation of GNSS receivers until denying its operation.

Classification Federated Learning +1

Recursive classification of satellite imaging time-series: An application to water mapping, land cover classification and deforestation detection

no code implementations • 4 Jan 2023 • Helena Calatrava, Bhavya Duvvuri, Haoqing Li, Ricardo Borsoi, Edward Beighley, Deniz Erdogmus, Pau Closas, Tales Imbiriba

Our method also improves the performance of deep learning-based classifiers without the need for additional training data.

Classification Decision Making +3