Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Amos Storkey

Better Training using Weight-Constrained Stochastic Dynamics


Jun 20, 2021
Benedict Leimkuhler, Tiffany Vlaar, Timothée Pouchon, Amos Storkey

* Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021 
* ICML 2021 camera-ready. arXiv admin note: substantial text overlap with arXiv:2006.10114 

  Access Paper or Ask Questions

How Sensitive are Meta-Learners to Dataset Imbalance?


Apr 12, 2021
Mateusz Ochal, Massimiliano Patacchiola, Amos Storkey, Jose Vazquez, Sen Wang

* Published as a workshop paper at the Learning to Learn workshop at ICLR 2021. arXiv admin note: text overlap with arXiv:2101.02523 

  Access Paper or Ask Questions

Few-Shot Learning with Class Imbalance


Jan 07, 2021
Mateusz Ochal, Massimiliano Patacchiola, Amos Storkey, Jose Vazquez, Sen Wang

* [Under Review] 

  Access Paper or Ask Questions

Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks


Nov 19, 2020
Luke Darlow, Stanisław Jastrzębski, Amos Storkey

* 10 pages, 4 figures, submitted to AISTATS 2021 

  Access Paper or Ask Questions

Non-greedy Gradient-based Hyperparameter Optimization Over Long Horizons


Jul 15, 2020
Paul Micaelli, Amos Storkey


  Access Paper or Ask Questions

Constraint-Based Regularization of Neural Networks


Jun 17, 2020
Benedict Leimkuhler, Timothée Pouchon, Tiffany Vlaar, Amos Storkey


  Access Paper or Ask Questions

Optimizing Grouped Convolutions on Edge Devices


Jun 17, 2020
Perry Gibson, José Cano, Jack Turner, Elliot J. Crowley, Michael O'Boyle, Amos Storkey

* Camera ready version to be published at ASAP 2020 - The 31st IEEE International Conference on Application-specific Systems, Architectures and Processors. 8 pages, 6 figures 

  Access Paper or Ask Questions

Self-Supervised Relational Reasoning for Representation Learning


Jun 10, 2020
Massimiliano Patacchiola, Amos Storkey


  Access Paper or Ask Questions

Neural Architecture Search without Training


Jun 08, 2020
Joseph Mellor, Jack Turner, Amos Storkey, Elliot J. Crowley


  Access Paper or Ask Questions

Defining Benchmarks for Continual Few-Shot Learning


Apr 15, 2020
Antreas Antoniou, Massimiliano Patacchiola, Mateusz Ochal, Amos Storkey


  Access Paper or Ask Questions

Meta-Learning in Neural Networks: A Survey


Apr 11, 2020
Timothy Hospedales, Antreas Antoniou, Paul Micaelli, Amos Storkey


  Access Paper or Ask Questions

DHOG: Deep Hierarchical Object Grouping


Mar 13, 2020
Luke Nicholas Darlow, Amos Storkey

* 15 pages, submitted to ECCV 2020 

  Access Paper or Ask Questions

What Information Does a ResNet Compress?


Mar 13, 2020
Luke Nicholas Darlow, Amos Storkey

* 10 pages + appendices; submitted to ICLR 2019 

  Access Paper or Ask Questions

Comparing recurrent and convolutional neural networks for predicting wave propagation


Mar 09, 2020
Stathi Fotiadis, Eduardo Pignatelli, Mario Lino Valencia, Chris Cantwell, Amos Storkey, Anil A. Bharath


  Access Paper or Ask Questions

Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs


Feb 20, 2020
Valentin Radu, Kuba Kaszyk, Yuan Wen, Jack Turner, Jose Cano, Elliot J. Crowley, Bjorn Franke, Amos Storkey, Michael O'Boyle

* A copy of this was published in IISWC'19 

  Access Paper or Ask Questions

Deep Kernel Transfer in Gaussian Processes for Few-shot Learning


Oct 11, 2019
Massimiliano Patacchiola, Jack Turner, Elliot J. Crowley, Amos Storkey


  Access Paper or Ask Questions

BlockSwap: Fisher-guided Block Substitution for Network Compression


Jun 10, 2019
Jack Turner, Elliot J. Crowley, Gavin Gray, Amos Storkey, Michael O'Boyle


  Access Paper or Ask Questions

Separable Layers Enable Structured Efficient Linear Substitutions


Jun 03, 2019
Gavin Gray, Elliot J. Crowley, Amos Storkey


  Access Paper or Ask Questions

Learning to learn via Self-Critique


May 31, 2019
Antreas Antoniou, Amos Storkey

* Under Review 

  Access Paper or Ask Questions

Learning to learn by Self-Critique


May 27, 2019
Antreas Antoniou, Amos Storkey

* Under Review 

  Access Paper or Ask Questions

Zero-shot Knowledge Transfer via Adversarial Belief Matching


May 24, 2019
Paul Micaelli, Amos Storkey


  Access Paper or Ask Questions

Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation


Mar 05, 2019
Antreas Antoniou, Amos Storkey

* Work in Progress - Under Review in ICML 2019 

  Access Paper or Ask Questions

Dilated DenseNets for Relational Reasoning


Nov 01, 2018
Antreas Antoniou, Agnieszka SĹ‚owik, Elliot J. Crowley, Amos Storkey

* Extended Abstract 

  Access Paper or Ask Questions

Exploration by Random Network Distillation


Oct 30, 2018
Yuri Burda, Harrison Edwards, Amos Storkey, Oleg Klimov


  Access Paper or Ask Questions

HAKD: Hardware Aware Knowledge Distillation


Oct 24, 2018
Jack Turner, Elliot J. Crowley, Valentin Radu, José Cano, Amos Storkey, Michael O'Boyle


  Access Paper or Ask Questions

How to train your MAML


Oct 22, 2018
Antreas Antoniou, Harrison Edwards, Amos Storkey

* ICLR under review 

  Access Paper or Ask Questions

Moonshine: Distilling with Cheap Convolutions


Oct 22, 2018
Elliot J. Crowley, Gavin Gray, Amos Storkey

* NIPS 2018 

  Access Paper or Ask Questions

Pruning neural networks: is it time to nip it in the bud?


Oct 10, 2018
Elliot J. Crowley, Jack Turner, Amos Storkey, Michael O'Boyle

* Extended Abstract 

  Access Paper or Ask Questions

Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks


Sep 19, 2018
Jack Turner, José Cano, Valentin Radu, Elliot J. Crowley, Michael O'Boyle, Amos Storkey

* IISWC 2018 

  Access Paper or Ask Questions