196 citations · 448 across the 19 of their papers we have counts for
19 papers
Generalisation and the Risk--Entropy Curve
Dominic Belcher, Antonia Marcu, Adam Prügel-Bennett
In this paper we show that the expected generalisation performance of a learning machine is determined by the distribution of risks or equivalently its logarithm -- a quantity we t…
Orthogonalising gradients to speed up neural network optimisation
Mark Tuddenham, Adam Prügel-Bennett, Jonathan Hare
The optimisation of neural networks can be sped up by orthogonalising the gradients before the optimisation step, ensuring the diversification of the learned representations. We or…
On Data-centric Myths
Antonia Marcu, Adam Prügel-Bennett
The community lacks theory-informed guidelines for building good data sets. We analyse theoretical directions relating to what aspects of the data matter and conclude that the intu…
On the Effects of Artificial Data Modification
Antonia Marcu, Adam Prügel-Bennett
Data distortion is commonly applied in vision models during both training (e.g methods like MixUp and CutMix) and evaluation (e.g. shape-texture bias and robustness). This data mod…
GeoCLR: Georeference Contrastive Learning for Efficient Seafloor Image Interpretation
Takaki Yamada, Adam Prügel-Bennett, Stefan B. Williams +2
This paper describes Georeference Contrastive Learning of visual Representation (GeoCLR) for efficient training of deep-learning Convolutional Neural Networks (CNNs). The method le…
Language Models as Zero-shot Visual Semantic Learners
Yue Jiao, Jonathon Hare, Adam Prügel-Bennett
Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approache…
What Remains of Visual Semantic Embeddings
Yue Jiao, Jonathon Hare, Adam Prügel-Bennett
Zero shot learning (ZSL) has seen a surge in interest over the decade for its tight links with the mechanism making young children recognize novel objects. Although different parad…
Object detection for crabs in top-view seabed imagery
Vlad Velici, Adam Prügel-Bennett
This report presents the application of object detection on a database of underwater images of different species of crabs, as well as aerial images of sea lions and finally the Pas…
RotLSTM: Rotating Memories in Recurrent Neural Networks
Vlad Velici, Adam Prügel-Bennett
Long Short-Term Memory (LSTM) units have the ability to memorise and use long-term dependencies between inputs to generate predictions on time series data. We introduce the concept…
Quasi-Newton's method in the class gradient defined high-curvature subspace
Mark Tuddenham, Adam Prügel-Bennett, Jonathan Hare
Classification problems using deep learning have been shown to have a high-curvature subspace in the loss landscape equal in dimension to the number of classes. Moreover, this subs…
Linear Disentangled Representations and Unsupervised Action Estimation
Matthew Painter, Jonathon Hare, Adam Prugel-Bennett
Disentangled representation learning has seen a surge in interest over recent times, generally focusing on new models which optimise one of many disparate disentanglement metrics.…
FMix: Enhancing Mixed Sample Data Augmentation
Ethan Harris, Antonia Marcu, Matthew Painter +3
Mixed Sample Data Augmentation (MSDA) has received increasing attention in recent years, with many successful variants such as MixUp and CutMix. By studying the mutual information…
Rethinking Generalisation
Antonia Marcu, Adam Prügel-Bennett
In this paper, a new approach to computing the generalisation performance is presented that assumes the distribution of risks, , for a learning scenario is known. From this,…
Deep Set Prediction Networks
Yan Zhang, Jonathon Hare, Adam Prügel-Bennett
Current approaches for predicting sets from feature vectors ignore the unordered nature of sets and suffer from discontinuity issues as a result. We propose a general model for pre…
FSPool: Learning Set Representations with Featurewise Sort Pooling
Yan Zhang, Jonathon Hare, Adam Prügel-Bennett
Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem. We introduce a pooling method for sets of feature vectors ba…
Minimum description length as an objective function for non-negative matrix factorization
Steven Squires, Adam Prugel Bennett, Mahesan Niranjan
Non-negative matrix factorization (NMF) is a dimensionality reduction technique which tends to produce a sparse representation of data. Commonly, the error between the actual and r…
Learning Representations of Sets through Optimized Permutations
Yan Zhang, Jonathon Hare, Adam Prügel-Bennett
Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns h…
Learning to Count Objects in Natural Images for Visual Question Answering
Yan Zhang, Jonathon Hare, Adam Prügel-Bennett
Visual Question Answering (VQA) models have struggled with counting objects in natural images so far. We identify a fundamental problem due to soft attention in these models as a c…
Extended Formulations for Online Linear Bandit Optimization
Shaona Ghosh, Adam Prugel-Bennett
On-line linear optimization on combinatorial action sets (d-dimensional actions) with bandit feedback, is known to have complexity in the order of the dimension of the problem. The…