b'Amos Storkey'

research

∙ 08/03/2023

Diffusion Models for Counterfactual Generation and Anomaly Detection in Brain Images

Segmentation masks of pathological areas are useful in many medical appl...

0 Alessandro Fontanella, et al. ∙

research

∙ 07/25/2023

QuickQual: Lightweight, convenient retinal image quality scoring with off-the-shelf pretrained models

Image quality remains a key problem for both traditional and deep learni...

0 Justin Engelmann, et al. ∙

research

∙ 07/24/2023

Label Noise: Correcting a Correction

Training neural network classifiers on datasets with label noise poses a...

0 William Toner, et al. ∙

research

∙ 07/03/2023

Efficient and fully-automatic retinal choroid segmentation in OCT through DL-based distillation of a hand-crafted pipeline

Retinal vascular phenotypes, derived from low-cost, non-invasive retinal...

0 Jamie Burke, et al. ∙

research

∙ 05/30/2023

Class Conditional Gaussians for Continual Learning

Dealing with representation shift is one of the main problems in online ...

0 Thomas L. Lee, et al. ∙

research

∙ 03/27/2023

ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging

In some medical imaging tasks and other settings where only small parts ...

0 Alessandro Fontanella, et al. ∙

research

∙ 01/30/2023

Contrastive Meta-Learning for Partially Observable Few-Shot Learning

Many contrastive and meta-learning approaches learn representations by i...

19 Adam Jelley, et al. ∙

research

∙ 07/12/2022

Robust and efficient computation of retinal fractal dimension through deep approximation

A retinal trait, or phenotype, summarises a specific aspect of a retinal...

17 Justin Engelmann, et al. ∙

research

∙ 07/05/2022

Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning

Successful deployment of multi-agent reinforcement learning often requir...

14 Lukas Schäfer, et al. ∙

research

∙ 03/11/2022

Detection of multiple retinal diseases in ultra-widefield fundus images using deep learning: data-driven identification of relevant regions

Ultra-widefield (UWF) imaging is a promising modality that captures a la...

4 Justin Engelmann, et al. ∙

research

∙ 03/10/2022

Prediction-Guided Distillation for Dense Object Detection

Real-world object detection models should be cheap and accurate. Knowled...

0 Chenhongyi Yang, et al. ∙

research

∙ 12/17/2021

Global explainability in aligned image modalities

Deep learning (DL) models are very effective on many computer vision pro...

6 Justin Engelmann, et al. ∙

research

∙ 12/02/2021

Hamiltonian prior to Disentangle Content and Motion in Image Sequences

We present a deep latent variable model for high dimensional sequential ...

5 Asif Khan, et al. ∙

research

∙ 06/20/2021

Better Training using Weight-Constrained Stochastic Dynamics

We employ constraints to control the parameter space of deep neural netw...

23 Benedict Leimkuhler, et al. ∙

research

∙ 04/12/2021

How Sensitive are Meta-Learners to Dataset Imbalance?

Meta-Learning (ML) has proven to be a useful tool for training Few-Shot ...

29 Mateusz Ochal, et al. ∙

research

∙ 01/07/2021

Few-Shot Learning with Class Imbalance

Few-shot learning aims to train models on a limited number of labeled sa...

45 Mateusz Ochal, et al. ∙

research

∙ 11/19/2020

Latent Adversarial Debiasing: Mitigating Collider Bias in Deep Neural Networks

Collider bias is a harmful form of sample selection bias that neural net...

5 Luke Darlow, et al. ∙

research

∙ 07/15/2020

Non-greedy Gradient-based Hyperparameter Optimization Over Long Horizons

Gradient-based hyperparameter optimization is an attractive way to perfo...

18 Paul Micaelli, et al. ∙

research

∙ 06/17/2020

Constraint-Based Regularization of Neural Networks

We propose a method for efficiently incorporating constraints into a sto...

14 Benedict Leimkuhler, et al. ∙

research

∙ 06/17/2020

Optimizing Grouped Convolutions on Edge Devices

When deploying a deep neural network on constrained hardware, it is poss...

11 Perry Gibson, et al. ∙

research

∙ 06/10/2020

Self-Supervised Relational Reasoning for Representation Learning

In self-supervised learning, a system is tasked with achieving a surroga...

13 Massimiliano Patacchiola, et al. ∙

research

∙ 06/08/2020

Neural Architecture Search without Training

The time and effort involved in hand-designing deep neural networks is i...

7 Joseph Mellor, et al. ∙

research

∙ 04/11/2020

Meta-Learning in Neural Networks: A Survey

The field of meta-learning, or learning-to-learn, has seen a dramatic ri...

82 Timothy Hospedales, et al. ∙

research

∙ 03/13/2020

DHOG: Deep Hierarchical Object Grouping

Recently, a number of competitive methods have tackled unsupervised repr...

0 Luke Nicholas Darlow, et al. ∙

research

∙ 03/13/2020

What Information Does a ResNet Compress?

The information bottleneck principle (Shwartz-Ziv Tishby, 2017) sugg...

4 Luke Nicholas Darlow, et al. ∙

research

∙ 02/20/2020

Comparing recurrent and convolutional neural networks for predicting wave propagation

Dynamical systems can be modelled by partial differential equations and ...

4 Stathi Fotiadis, et al. ∙

research

∙ 02/20/2020

Performance Aware Convolutional Neural Network Channel Pruning for Embedded GPUs

Convolutional Neural Networks (CNN) are becoming a common presence in ma...

7 Valentin Radu, et al. ∙

research

∙ 10/11/2019

Deep Kernel Transfer in Gaussian Processes for Few-shot Learning

Humans tackle new problems by making inferences that go far beyond the i...

31 Massimiliano Patacchiola, et al. ∙

research

∙ 06/10/2019

BlockSwap: Fisher-guided Block Substitution for Network Compression

The desire to run neural networks on low-capacity edge devices has led t...

2 Jack Turner, et al. ∙

research

∙ 06/03/2019

Separable Layers Enable Structured Efficient Linear Substitutions

In response to the development of recent efficient dense layers, this pa...

2 Gavin Gray, et al. ∙

research

∙ 05/24/2019

Learning to learn by Self-Critique

In few-shot learning, a machine learning system learns from a small set ...

11 Antreas Antoniou, et al. ∙

research

∙ 05/23/2019

Zero-shot Knowledge Transfer via Adversarial Belief Matching

Performing knowledge transfer from a large teacher network to a smaller ...

2 Paul Micaelli, et al. ∙

research

∙ 02/26/2019

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

The field of few-shot learning has been laboriously explored in the supe...

6 Antreas Antoniou, et al. ∙

research

∙ 11/01/2018

Dilated DenseNets for Relational Reasoning

Despite their impressive performance in many tasks, deep neural networks...

11 Antreas Antoniou, et al. ∙

research

∙ 10/30/2018

Exploration by Random Network Distillation

We introduce an exploration bonus for deep reinforcement learning method...

0 Yuri Burda, et al. ∙

research

∙ 10/24/2018

HAKD: Hardware Aware Knowledge Distillation

Despite recent developments, deploying deep neural networks on resource ...

10 Jack Turner, et al. ∙

research

∙ 10/24/2018

Distilling with Performance Enhanced Students

The task of accelerating large neural networks on general purpose hardwa...

0 Jack Turner, et al. ∙

research

∙ 10/22/2018

How to train your MAML

The field of few-shot learning has recently seen substantial advancement...

8 Antreas Antoniou, et al. ∙

research

∙ 10/10/2018

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

Pruning is a popular technique for compressing a neural network: a large...

6 Elliot J. Crowley, et al. ∙

research

∙ 09/19/2018

Characterising Across-Stack Optimisations for Deep Convolutional Neural Networks

Convolutional Neural Networks (CNNs) are extremely computationally deman...

4 Jack Turner, et al. ∙

research

∙ 08/13/2018

Large-Scale Study of Curiosity-Driven Learning

Reinforcement learning algorithms rely on carefully engineering environm...

0 Yuri Burda, et al. ∙

research

∙ 07/13/2018

DNN's Sharpest Directions Along the SGD Trajectory

Recent work has identified that using a high learning rate or a small ba...

4 Stanisław Jastrzębski, et al. ∙

research

∙ 11/13/2017

Three Factors Influencing Minima in SGD

We study the properties of the endpoint of stochastic gradient descent (...

0 Stanisław Jastrzębski, et al. ∙

research

∙ 11/12/2017

Data Augmentation Generative Adversarial Networks

Effective training of neural networks requires much data. In the low-dat...

0 Antreas Antoniou, et al. ∙

research

∙ 11/07/2017

Moonshine: Distilling with Cheap Convolutions

Model distillation compresses a trained machine learning model, such as ...

0 Elliot J. Crowley, et al. ∙

research

∙ 06/07/2016

Towards a Neural Statistician

An efficient learner is one who reuses what they already know to tackle ...

0 Harrison Edwards, et al. ∙

research

∙ 11/18/2015

Censoring Representations with an Adversary

In practice, there are often explicit constraints on what representation...

0 Harrison Edwards, et al. ∙

research

∙ 12/10/2014

Teaching Deep Convolutional Neural Networks to Play Go

Mastering the game of Go has remained a long standing challenge to the f...

0 Christopher Clark, et al. ∙

research

∙ 03/04/2014

Multi-period Trading Prediction Markets with Connections to Machine Learning

We present a new model for prediction markets, in which we use risk meas...

0 Jinli Hu, et al. ∙

research

∙ 09/27/2013

Bayesian Inference in Sparse Gaussian Graphical Models

One of the fundamental tasks of science is to find explainable relations...

0 Peter Orchard, et al. ∙

Amos Storkey

Featured Co-authors