Anatomically Constrained ResNets Exhibit Opponent Receptive Fields; So What?

no code implementations • NeurIPS Workshop SVRHM 2020 • Ethan Harris, Daniela Mihai, Jonathon Hare

Primate visual systems are well known to exhibit varying degrees of bottlenecks in the early visual pathway.

How Convolutional Neural Network Architecture Biases Learned Opponency and Colour Tuning

1 code implementation • 6 Oct 2020 • Ethan Harris, Daniela Mihai, Jonathon Hare

The colour tuning data can further be used to form a rich understanding of how colour is encoded by a network.

FMix: Enhancing Mixed Sample Data Augmentation

5 code implementations • 27 Feb 2020 • Ethan Harris, Antonia Marcu, Matthew Painter, Mahesan Niranjan, Adam Prügel-Bennett, Jonathon Hare

Finally, we show that a consequence of the difference between interpolating MSDA such as MixUp and masking MSDA such as FMix is that the two can be combined to improve performance even further.

Data Augmentation Image Classification

Spatial and Colour Opponency in Anatomically Constrained Deep Networks

1 code implementation • 14 Oct 2019 • Ethan Harris, Daniela Mihai, Jonathon Hare

Colour vision has long fascinated scientists, who have sought to understand both the physiology of the mechanics of colour vision and the psychophysics of colour perception.

A Biologically Inspired Visual Working Memory for Deep Networks

2 code implementations • ICLR 2019 • Ethan Harris, Mahesan Niranjan, Jonathon Hare

The state of our Hebb-Rosenblatt memory is embedded in STAWM as the weights space of a layer.

Classification General Classification

Torchbearer: A Model Fitting Library for PyTorch

2 code implementations • 10 Sep 2018 • Ethan Harris, Matthew Painter, Jonathon Hare

We introduce torchbearer, a model fitting library for pytorch aimed at researchers working on deep learning or differentiable programming.

Data Visualization