3 papers
cs.LG2019
Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural Networks
Juan Maroñas, Roberto Paredes, Daniel Ramos
Deep Neural Networks (DNNs) have achieved state-of-the-art accuracy performance in many tasks. However, recent works have pointed out that the outputs provided by these models are…
cs.LG2019
Generative Models For Deep Learning with Very Scarce Data
Juan Maroñas, Roberto Paredes, Daniel Ramos
The goal of this paper is to deal with a data scarcity scenario where deep learning techniques use to fail. We compare the use of two well established techniques, Restricted Boltzm…
cs.CV2018
Improving Automated Latent Fingerprint Identification using Extended Minutia Types
Ram P. Krish, Julian Fierrez, Daniel Ramos +2
Latent fingerprints are usually processed with Automated Fingerprint Identification Systems (AFIS) by law enforcement agencies to narrow down possible suspects from a criminal data…