6 citations · 8 across the 4 of their papers we have counts for
4 papers
Function-space Parameterization of Neural Networks for Sequential Learning
Aidan Scannell, Riccardo Mereu, Paul Chang +3
Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining prior knowledge. While Gaussian processes el…
Sparse Function-space Representation of Neural Networks
Aidan Scannell, Riccardo Mereu, Paul Chang +3
Deep neural networks (NNs) are known to lack uncertainty estimates and struggle to incorporate new data. We present a method that mitigates these issues by converting NNs from weig…
Learning Sequential Descriptors for Sequence-based Visual Place Recognition
Riccardo Mereu, Gabriele Trivigno, Gabriele Berton +2
In robotics, Visual Place Recognition is a continuous process that receives as input a video stream to produce a hypothesis of the robot's current position within a map of known pl…
The Borexino Thermal Monitoring & Management System and simulations of the fluid-dynamics of the Borexino detector under asymmetrical, changing boundary conditions
D. Bravo-Berguño, R. Mereu, P. Cavalcante +9
A comprehensive monitoring system for the thermal environment inside the Borexino neutrino detector was developed and installed in order to reduce uncertainties in determining temp…