• Publications
  • Influence
FMix: Enhancing Mixed Sample Data Augmentation
TLDR
We propose FMix, an MSDA that uses binary masks obtained by applying a threshold to low frequency images sampled from Fourier space, obtaining new state-of-the-art results on CIFAR-10 and Fashion-MNIST. Expand
  • 18
  • 2
  • PDF
Understanding and Enhancing Mixed Sample Data Augmentation
TLDR
We analyse MixUp, CutMix, and FMix from an information theoretic perspective, characterising learned models in terms of how they progressively compress the input with depth. Expand
  • 8
  • 2
Automatic Face Recognition Using Stereo Images
TLDR
We show that optical images obtained with a pair of stereo cameras may be used to extract depth information in the form of disparity values, and thereby significantly enhance the performance of a face recognition system. Expand
  • 15
  • 1
  • PDF
Partial correlation financial networks
TLDR
Correlation networks have been a popular way of inferring a financial network due to the simplicity of construction and the ease of interpretability. Expand
  • 8
A Method of Integrating Spatial Proteomics and Protein-Protein Interaction Network Data
TLDR
We provide a method of integrating spatial proteomics data together with protein-protein interaction (PPI) networks to enable the extraction of more information. Expand
  • 2
  • PDF
Quantifying Influence in Financial Markets via Partial Correlation Network Inference
TLDR
We infer partial correlation networks from daily S&P500 returns, study how these networks vary over time and draw parallels to the macroeconomic events that may explain the changes. Expand
  • 3
Saliency Map on Cnns for Protein Secondary Structure Prediction
TLDR
Saliency maps for protein secondary structure prediction using the techniques of saliency maps. Expand
  • 1
An evaluation of different classification algorithms for protein sequence-based reverse vaccinology prediction
TLDR
An evaluation of different classification algorithms for protein sequence-based reverse vaccinology prediction. Expand
  • 1
  • PDF
Robust subspace methods for outlier detection in genomic data circumvents the curse of dimensionality
The application of machine learning to inference problems in biology is dominated by supervised learning problems of regression and classification, and unsupervised learning problems of clusteringExpand
  • 1
  • PDF
Representation-dimensionality Trade-off in Biological Sequence-based Inference
TLDR
We demonstrate a trade-off between fidelity of representation of amino acids of proteins and the resulting dimensionality of the embedding space. Expand
  • 1