5 papers
Explicit Regularisation in Gaussian Noise Injections
Alexander Camuto, Matthew Willetts, Umut Şimşekli +2
We study the regularisation induced in neural networks by Gaussian noise injections (GNIs). Though such injections have been extensively studied when applied to data, there have be…
Towards a Theoretical Understanding of the Robustness of Variational Autoencoders
Alexander Camuto, Matthew Willetts, Stephen Roberts +2
We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations. While previous work has developed algorit…
Learning Bijective Feature Maps for Linear ICA
Alexander Camuto, Matthew Willetts, Brooks Paige +2
Separating high-dimensional data like images into independent latent factors, i.e independent component analysis (ICA), remains an open research problem. As we show, existing proba…
Regularising Deep Networks with Deep Generative Models
Matthew Willetts, Alexander Camuto, Stephen Roberts +1
We develop a new method for regularising neural networks. We learn a probability distribution over the activations of all layers of the model and then insert imputed values into th…
Improving VAEs' Robustness to Adversarial Attack
Matthew Willetts, Alexander Camuto, Tom Rainforth +2
Variational autoencoders (VAEs) have recently been shown to be vulnerable to adversarial attacks, wherein they are fooled into reconstructing a chosen target image. However, how to…