no code implementations • 5 Sep 2022 • Ángel González-Prieto, Alberto Mozo, Edgar Talavera, Sandra Gómez-Canaval
By studying the dynamics of the truncated Fourier series for the continuous Alternating Gradient Descend algorithm, we are able to approximate the real flow and to identify the main features of the convergence of the GAN.
no code implementations • 25 Jun 2022 • Guillermo Iglesias, Edgar Talavera, Ángel González-Prieto, Alberto Mozo, Sandra Gómez-Canaval
With the latest advances in Deep Learning-based generative models, it has not taken long to take advantage of their remarkable performance in the area of time series.
no code implementations • 29 Oct 2021 • Ángel González-Prieto, Alberto Mozo, Sandra Gómez-Canaval, Edgar Talavera
In sharp contrast with previous works, our activation function provides a more general approach that deals not only with the replication of categorical variables but with any type of data distribution (continuous or discrete).
no code implementations • 30 Jul 2021 • Alberto Mozo, Ángel González-Prieto, Antonio Pastor, Sandra Gómez-Canaval, Edgar Talavera
Data privacy is appearing more and more as a strong requirement when processing such network data, which suggests to find solutions where synthetic data can fully replace real data.
no code implementations • 12 Apr 2018 • Bruno Ordozgoiti, Alberto Mozo, Jesús García López de Lacalle
The Column Subset Selection Problem provides a natural framework for unsupervised feature selection.
no code implementations • 24 Oct 2016 • Udi Margolin, Alberto Mozo, Bruno Ordozgoiti, Danny Raz, Elisha Rosensweig, Itai Segall
5G networks are expected to be more dynamic and chaotic in their structure than current networks.