Search Results for author: Joseph Mellor

Found 2 papers, 1 papers with code

Neural Architecture Search without Training

2 code implementations8 Jun 2020 Joseph Mellor, Jack Turner, Amos Storkey, Elliot J. Crowley

In this work, we examine the overlap of activations between datapoints in untrained networks and motivate how this can give a measure which is usefully indicative of a network's trained performance.

Neural Architecture Search

Better Boosting with Bandits for Online Learning

no code implementations16 Jan 2020 Nikolaos Nikolaou, Joseph Mellor, Nikunj C. Oza, Gavin Brown

The outputs of the ensemble need to be properly calibrated before they can be used as probability estimates.

Cannot find the paper you are looking for? You can Submit a new open access paper.