activity
20182026
most citedSeparable Layers Enable Structured Efficient Linear Substitutions

3 citations · 5 across the 6 of their papers we have counts for

collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML20193 cited

Separable Layers Enable Structured Efficient Linear Substitutions

Gavin Gray, Elliot J. Crowley, Amos Storkey

In response to the development of recent efficient dense layers, this paper shows that something as simple as replacing linear components in pointwise convolutions with structured…

stat.ML2018

Dilated DenseNets for Relational Reasoning

Antreas Antoniou, Agnieszka Słowik, Elliot J. Crowley +1

Despite their impressive performance in many tasks, deep neural networks often struggle at relational reasoning. This has recently been remedied with the introduction of a plug-in…

stat.ML2018

Distilling with Performance Enhanced Students

Jack Turner, Elliot J. Crowley, Valentin Radu +3

The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size. However, the efficacy o…

stat.ML2018

A Closer Look at Structured Pruning for Neural Network Compression

Elliot J. Crowley, Jack Turner, Amos Storkey +1

Structured pruning is a popular method for compressing a neural network: given a large trained network, one alternates between removing channel connections and fine-tuning; reducin…

stat.ML2018

Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks

Jack Turner, José Cano, Valentin Radu +3

Convolutional Neural Networks (CNNs) are extremely computationally demanding, presenting a large barrier to their deployment on resource-constrained devices. Since such systems are…