Publications from our Researchers

Several of our current PhD candidates and fellow researchers at the Data Science Institute have published, or in the proccess of publishing, papers to present their research.  

Citation

BibTex format

@article{Creswell,
author = {Creswell, A and Bharath, AA},
title = {Denoising Adversarial Autoencoders},
url = {http://arxiv.org/abs/1703.01220v3},
}

RIS format (EndNote, RefMan)

TY  - JOUR
AB - Unsupervised learning is of growing interest because it unlocks the potentialheld in vast amounts of unlabelled data to learn useful representations forinference. Autoencoders, a form of generative model, may be trained by learningto reconstruct unlabelled input data from a latent representation space. Morerobust representations may be produced by an autoencoder if it learns torecover clean input samples from corrupted ones. Representations may be furtherimproved by introducing regularisation during training to shape thedistribution of the encoded data in latent space. We suggest denoisingadversarial autoencoders, which combine denoising and regularisation, shapingthe distribution of latent space using adversarial training. We introduce anovel analysis that shows how denoising may be incorporated into the trainingand sampling of adversarial autoencoders. Experiments are performed to assessthe contributions that denoising makes to the learning of representations forclassification and sample synthesis. Our results suggest that autoencoderstrained using a denoising criterion achieve higher classification performance,and can synthesise samples that are more consistent with the input data thanthose trained without a corruption process.
AU - Creswell,A
AU - Bharath,AA
TI - Denoising Adversarial Autoencoders
UR - http://arxiv.org/abs/1703.01220v3
ER -