activity
20182021
most citedSearching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours

48 citations · 75 across the 3 of their papers we have counts for

collaborators

6 papers

astro-ph.IM202148 cited

Searching for changing-state AGNs in massive datasets -- I: applying deep learning and anomaly detection techniques to find AGNs with anomalous variability behaviours

P. Sánchez-Sáez, H. Lira, L. Martí +14

The classic classification scheme for Active Galactic Nuclei (AGNs) was recently challenged by the discovery of the so-called changing-state (changing-look) AGNs (CSAGNs). The phys…

cs.LG2020

MPCC: Matching Priors and Conditionals for Clustering

Nicolás Astorga, Pablo Huijse, Pavlos Protopapas +1

Clustering is a fundamental task in unsupervised learning that depends heavily on the data representation that is used. Deep generative models have appeared as a promising tool to…

cs.CV2020

Transformation Based Deep Anomaly Detection in Astronomical Images

Esteban Reyes, Pablo A. Estévez

In this work, we propose several enhancements to a geometric transformation based model for anomaly detection in images (GeoTranform). The model assumes that the anomaly class is u…

eess.SP202017 cited

RED: Deep Recurrent Neural Networks for Sleep EEG Event Detection

Nicolás I. Tapia, Pablo A. Estévez

The brain electrical activity presents several short events during sleep that can be observed as distinctive micro-structures in the electroencephalogram (EEG), such as sleep spind…

cs.LG202010 cited

On the Information Plane of Autoencoders

Nicolás I. Tapia, Pablo A. Estévez

The training dynamics of hidden layers in deep learning are poorly understood in theory. Recently, the Information Plane (IP) was proposed to analyze them, which is based on the in…

astro-ph.EP2018

Asteroids in the High cadence Transient Survey

J. Peña, C. Fuentes, F. Förster +11

We report on the serendipitous observations of Solar System objects imaged during the High cadence Transient Survey (HiTS) 2014 observation campaign. Data from this high cadence, w…