Search or filter publications

Filter by type:

Filter by publication type

Filter by year:

to

Results

  • Showing results for:
  • Reset all filters

Search results

  • JOURNAL ARTICLE
    Creswell A, Bharath AA,

    Task Specific Adversarial Cost Function

    The cost function used to train a generative model should fit the purpose ofthe model. If the model is intended for tasks such as generating perceptuallycorrect samples, it is beneficial to maximise the likelihood of a sample drawnfrom the model, Q, coming from the same distribution as the training data, P.This is equivalent to minimising the Kullback-Leibler (KL) distance, KL[Q||P].However, if the model is intended for tasks such as retrieval or classificationit is beneficial to maximise the likelihood that a sample drawn from thetraining data is captured by the model, equivalent to minimising KL[P||Q]. Thecost function used in adversarial training optimises the Jensen-Shannon entropywhich can be seen as an even interpolation between KL[Q||P] and KL[P||Q]. Here,we propose an alternative adversarial cost function which allows easy tuning ofthe model for either task. Our task specific cost function is evaluated on adataset of hand-written characters in the following tasks: Generation,retrieval and one-shot learning.

  • JOURNAL ARTICLE
    Creswell A, Bharath AA,

    Denoising Adversarial Autoencoders

    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.

  • CONFERENCE PAPER
    Arulkumaran K, Dilokthanakul N, Shanahan M, Bharath AAet al., 2016,

    Classifying Options for Deep Reinforcement Learning.

  • JOURNAL ARTICLE
    Ciaccio EJ, Coromilas J, Wit AL, Peters NS, Garan Het al., 2016,

    Formation of reentrant circuits in the mid-myocardial infarct border zone

    , COMPUTERS IN BIOLOGY AND MEDICINE, Vol: 71, Pages: 205-213, ISSN: 0010-4825
  • JOURNAL ARTICLE
    Luther V, Linton NWF, Koa-Wing M, Lim PB, Jamil-Copley S, Qureshi N, Ng FS, Hayat S, Whinnett Z, Davies DW, Peters NS, Kanagaratnam Pet al., 2016,

    A Prospective Study of Ripple Mapping in Atrial Tachycardias A Novel Approach to Interpreting Activation in Low-Voltage Areas

    , CIRCULATION-ARRHYTHMIA AND ELECTROPHYSIOLOGY, Vol: 9, ISSN: 1941-3149
  • JOURNAL ARTICLE
    Ma Z-B, Yang Y, Liu Y-X, Bharath AAet al., 2016,

    Recurrently Decomposable 2-D Convolvers for FPGA-Based Digital Image Processing

    , IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, Vol: 63, Pages: 979-983, ISSN: 1549-7747
  • CONFERENCE PAPER
    Ali RL, Cantwell CD, Qureshi NA, Roney CH, Lim PB, Sherwin SJ, Siggers JH, Peters NSet al., 2015,

    Automated fiducial point selection for reducing registration error in the co-localisation of left atrium electroanatomic and imaging data

    , 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Publisher: IEEE, Pages: 1989-1992, ISSN: 1557-170X
  • JOURNAL ARTICLE
    Cantwell CD, Roney CH, Ng FS, Siggers JH, Sherwin SJ, Peters NSet al., 2015,

    Techniques for automated local activation time annotation and conduction velocity estimation in cardiac mapping

    , COMPUTERS IN BIOLOGY AND MEDICINE, Vol: 65, Pages: 229-242, ISSN: 0010-4825
  • JOURNAL ARTICLE
    Christensen K, Manani KA, Peters NS, 2015,

    Simple Model for Identifying Critical Regions in Atrial Fibrillation

    , PHYSICAL REVIEW LETTERS, Vol: 114, ISSN: 0031-9007
  • JOURNAL ARTICLE
    Ciaccio EJ, Coromilas J, Ashikaga H, Cervantes DO, Wit AL, Peters NS, McVeigh ER, Garan Het al., 2015,

    Model of unidirectional block formation leading to reentrant ventricular tachycardia in the infarct border zone of postinfarction canine hearts

    , COMPUTERS IN BIOLOGY AND MEDICINE, Vol: 62, Pages: 254-263, ISSN: 0010-4825

This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.

Request URL: http://wlsprd.imperial.ac.uk:80/respub/WEB-INF/jsp/search-t4-html.jsp Request URI: /respub/WEB-INF/jsp/search-t4-html.jsp Query String: id=874&limit=10&respub-action=search.html Current Millis: 1506229966135 Current Time: Sun Sep 24 06:12:46 BST 2017