research
∙
05/03/2023
Normalizing flows for lattice gauge theory in arbitrary space-time dimension
Applications of normalizing flows to the sampling of field configuration...
share
research
∙
02/20/2023
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
Skip connections and normalisation layers form two standard architectura...
research
∙
11/14/2022
Aspects of scaling and scalability for flow-based sampling of lattice QCD
Recent applications of machine-learned normalizing flows to sampling in ...
research
∙
03/15/2022
Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers
Training very deep neural networks is still an extremely challenging tas...
research
∙
11/10/2021
SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision
A recently proposed class of models attempts to learn latent dynamics fr...
research
∙
11/09/2021
Which priors matter? Benchmarking models for learning latent dynamics
Learning dynamics is at the heart of many important applications of mach...
research
∙
11/13/2020
Better, Faster Fermionic Neural Networks
The Fermionic Neural Network (FermiNet) is a recently-developed neural n...
research
∙
06/23/2020
Disentangling by Subspace Diffusion
We present a novel nonparametric algorithm for symmetry-based disentangl...
research
∙
09/30/2019
Hamiltonian Generative Networks
The Hamiltonian formalism plays a central role in classical and quantum ...
research
∙
05/20/2018
Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
We introduce the Kronecker factored online Laplace approximation for ove...
research
∙
06/12/2017
Practical Gauss-Newton Optimisation for Deep Learning
We present an efficient block-diagonal ap- proximation to the Gauss-Newt...
research
∙
07/07/2016
Nesterov's Accelerated Gradient and Momentum as approximations to Regularised Update Descent
We present a unifying framework for adapting the update direction in gra...
research
∙
06/22/2016