Search Results for author: Matthew Willetts

Found 15 papers, 3 papers with code

I Don't Need $\mathbf{u}$: Identifiable Non-Linear ICA Without Side Information

no code implementations9 Jun 2021 Matthew Willetts, Brooks Paige

Recently there has been a renaissance in identifiability results in deep generative models, not least for non-linear ICA.

Variational Autoencoders: A Harmonic Perspective

no code implementations31 May 2021 Alexander Camuto, Matthew Willetts

We further demonstrate that adding Gaussian noise to the input of a VAE allows us to more finely control the frequency content and the Lipschitz constant of the VAE encoder networks.

Adversarial Robustness

Certifiably Robust Variational Autoencoders

no code implementations15 Feb 2021 Ben Barrett, Alexander Camuto, Matthew Willetts, Tom Rainforth

We introduce an approach for training Variational Autoencoders (VAEs) that are certifiably robust to adversarial attack.

Adversarial Attack

Relaxed-Responsibility Hierarchical Discrete VAEs

no code implementations14 Jul 2020 Matthew Willetts, Xenia Miscouridou, Stephen Roberts, Chris Holmes

Successfully training Variational Autoencoders (VAEs) with a hierarchy of discrete latent variables remains an area of active research.

Towards a Theoretical Understanding of the Robustness of Variational Autoencoders

no code implementations14 Jul 2020 Alexander Camuto, Matthew Willetts, Stephen Roberts, Chris Holmes, Tom Rainforth

We make inroads into understanding the robustness of Variational Autoencoders (VAEs) to adversarial attacks and other input perturbations.

Learning Bijective Feature Maps for Linear ICA

no code implementations18 Feb 2020 Alexander Camuto, Matthew Willetts, Brooks Paige, Chris Holmes, Stephen Roberts

Separating high-dimensional data like images into independent latent factors, i. e independent component analysis (ICA), remains an open research problem.

Non-Determinism in TensorFlow ResNets

no code implementations30 Jan 2020 Miguel Morin, Matthew Willetts

We show that the stochasticity in training ResNets for image classification on GPUs in TensorFlow is dominated by the non-determinism from GPUs, rather than by the initialisation of the weights and biases of the network or by the sequence of minibatches given.

Image Classification

Improving VAEs' Robustness to Adversarial Attack

no code implementations ICLR 2021 Matthew Willetts, Alexander Camuto, Tom Rainforth, Stephen Roberts, Chris Holmes

We make significant advances in addressing this issue by introducing methods for producing adversarially robust VAEs.

Adversarial Attack

Semi-Unsupervised Learning: Clustering and Classifying using Ultra-Sparse Labels

1 code implementation24 Jan 2019 Matthew Willetts, Stephen J. Roberts, Christopher C. Holmes

It could easily be the case that some classes of data are found only in the unlabelled dataset -- perhaps the labelling process was biased -- so we do not have any labelled examples to train on for some classes.

Semi-unsupervised Learning of Human Activity using Deep Generative Models

1 code implementation29 Oct 2018 Matthew Willetts, Aiden Doherty, Stephen Roberts, Chris Holmes

We introduce 'semi-unsupervised learning', a problem regime related to transfer learning and zero-shot learning where, in the training data, some classes are sparsely labelled and others entirely unlabelled.

Classification General Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.