Aidan Scannell
Aidan Scannell
Home
Publications
Talks
Posts
Projects
CV
Notes
bayesian-deep-learning
Function-space Prameterization of Neural Networks for Sequential Learning
Sequential learning paradigms pose challenges for gradient-based deep learning due to difficulties incorporating new data and retaining …
Aidan Scannell
,
Riccardo Mereu
,
Paul Chang
,
Ella Tamir
,
Joni Pajarinen
,
Arno Solin
PDF
Cite
Code
Poster
Slides
Website
(Function-space) Laplace Approximation for Bayesian Neural Networks
In this talk, I’ll present an overview of the Laplace approximation for quantifying uncertainty in Bayesian neural networks. …
Oct 3, 2023 4:30 PM — 5:30 PM
Zoom
Aidan Scannell
Slides
Sparse Function-space Representation of Neural Networks
Deep neural networks (NNs) are known to lack uncertainty estimates and struggle to incorporate new data. We present a method that …
Aidan Scannell
,
Riccardo Mereu
,
Paul Chang
,
Ella Tamir
,
Joni Pajarinen
,
Arno Solin
PDF
Cite
Code
Poster
Website
Cite
×