Chris Mingard

Train ImageNet without Hyperparameters with Automatic Gradient Descent
Machine Learning
Towards architecture-aware optimisation
Chris Mingard
April 19, 20239 min read
What can flatness teach us: understanding generalisation in Deep Neural Networks
Artificial Intelligence
This is the third post in a series summarising work that seeks to provide a theory of generalisation in Deep Neural Networks (DNNs)...
Chris Mingard
March 29, 202110 min read
Deep Neural Networks are biased, at initialisation, towards simple functions
And why is this a very important step in understanding why they work?
Chris Mingard
January 1, 20218 min read
Neural networks are fundamentally Bayesian
Deep Learning
Stochastic Gradient Descent approximates Bayesian sampling
Chris Mingard
December 19, 202016 min read

Train ImageNet without Hyperparameters with Automatic Gradient Descent