1 code implementation • NeurIPS 2020 • Will Williams, Sam Ringer, Tom Ash, John Hughes, David MacLeod, Jamie Dougherty
Despite progress in training neural networks for lossy image compression, current approaches fail to maintain both perceptual quality and abstract features at very low bitrates.
no code implementations • 18 Oct 2019 • Sam Ringer, Will Williams, Tom Ash, Remi Francis, David MacLeod
Accurate image classification given small amounts of labelled data (few-shot classification) remains an open problem in computer vision.
no code implementations • 6 Nov 2018 • Rémi Francis, Tom Ash, Will Williams
By fine-tuning the RNNLM on lattices with the average edit distance loss, we show that we obtain a 1. 9% relative improvement in word error rate over a purely generatively trained model.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • WS 2018 • Tom Ash, Remi Francis, Will Williams
Our entry to the parallel corpus filtering task uses a two-step strategy.
no code implementations • 2 Feb 2015 • Will Williams, Niranjani Prasad, David Mrva, Tom Ash, Tony Robinson
This paper investigates the scaling properties of Recurrent Neural Network Language Models (RNNLMs).