skip to content
Home

Cambridge Language Sciences

Interdisciplinary Research Centre
 

Prof Richard E. Turner

Research

My research lies at the interface between computer perception (which builds artificial systems for understanding images, sounds and videos), neuroscience (which tries to understand the brain) and machine-learning (which provides a theoretical framework for learning from data). The goal is to develop systems that solve important problems, drawing inspiration from the brain. For example, figuring out how many sound sources there are in an acoustic scene and what the individual contributions from each source are. There are medical and engineering applications of this work, such as in cochlear implants for the deaf. Importantly, the behaviour of these systems can also be compared to neural processing in the brain in order to better understand what the brain is doing.

Publications (from Symplectic)

Conference proceedings

2018 (Accepted for publication)

  • Turner, RE., Bui, T., Li, Y. and Cuong, N., 2018 (Accepted for publication). Variational continual learning

    • 2018

  • Tucker, G., Bhupatiraju, S., Gu, S., Turner, RE., Ghahramani, Z. and Levine, S., 2018. The Mirage of Action-Dependent Baselines in Reinforcement Learning Proceedings of Machine Learning Research, v. 80
    •
  • De Matthews, AGG., Hron, J., Rowland, M., Turner, RE. and Ghahramani, Z., 2018. Gaussian process behaviour in wide deep neural networks 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings,
    •

    2017

  • Tripuraneni, N., Rowland, M., Ghahramani, Z. and Turner, RE., 2017. Magnetic Hamiltonian Monte Carlo. ICML, v. 70
    •
  • Bui, TD., Nguyen, CV. and Turner, RE., 2017. Streaming sparse Gaussian process approximations Advances in Neural Information Processing Systems, v. 2017-December
    •
  • Turner, RE., Frellsen, J. and Navarro, A., 2017. The Multivariate Generalised von Mises distribution: Inference and applications Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (AAAI-17),
    •
  • Gu, S., Lillicrap, T., Ghahramani, Z., Turner, RE. and Levine, S., 2017. Q-PrOP: Sample-efficient policy gradient with an off-policy critic 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings,
    •
  • Jaques, N., Gu, S., Bahdanau, D., Hernández-Lobato, JM., Turner, RE. and Eck, D., 2017. Sequence tutor: Conservative fine-tuning of sequence generation models with KL-control 34th International Conference on Machine Learning, ICML 2017, v. 4
    •
  • Gu, S., Lillicrap, T., Ghahramani, Z., Turner, RE., Schölkopf, B. and Levine, S., 2017. Interpolated policy gradient: Merging on-policy and off-policy gradient estimation for deep reinforcement learning Advances in Neural Information Processing Systems, v. 2017-December
    •

    2016

  • Gu, S., Lillicrap, TP., Ghahramani, Z., Turner, RE. and Levine, S., 2016. Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic. CoRR, v. abs/1611.02247
    •
  • Bui, TD., Hernández-Lobato, JM., Hernández-Lobato, D., Li, Y. and Turner, RE., 2016. Deep Gaussian processes for regression using approximate expectation propagation 33rd International Conference on Machine Learning, ICML 2016, v. 3
    •
  • Li, Y. and Turner, RE., 2016. Rényi Divergence Variational Inference Advances in Neural Information Processing Systems 29 (NIPS 2016),
    •

    2015

  • Li, Y., Hernández-Lobato, JM. and Turner, RE., 2015. Stochastic expectation propagation Advances in Neural Information Processing Systems, v. 2015-January
    •
  • Tobar, F., Bui, TD. and Turner, RE., 2015. Learning stationary time series using Gaussian processes with nonparametric kernels Advances in Neural Information Processing Systems, v. 2015-January
    •
  • Bui, TD., Hernández-Lobato, JM., Li, Y., Hernández-Lobato, D. and Turner, RE., 2015. Training Deep Gaussian Processes using Stochastic Expectation Propagation and Probabilistic Backpropagation

    • 2010

  • Turner, RE. and Sahani, M., 2010. Statistical inference for single- and multi-band probabilistic amplitude demodulation. Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP),
    •

    2008

  • Turner, RE. and Sahani, M., 2008. Modeling natural sounds with modulation cascade processes Advances in Neural Information Processing Systems, v. 20
    •
  • Berkes, P., Turner, RE. and Sahani, M., 2008. On sparsity and overcompleteness in image models Advances in Neural Information Processing Systems, v. 20
    •

    2007

  • Turner, RE. and Sahani, M., 2007. Probabilistic Amplitude Demodulation 7th International Conference on Independent Component Analysis and Signal Separation,
    •
    Journal articles

    2018

  • Keshavarzi, M., Goehring, T., Zakis, J., Turner, RE. and Moore, BCJ., 2018. Use of a Deep Recurrent Neural Network to Reduce Wind Noise: Effects on Judged Speech Intelligibility and Sound Quality. Trends Hear, v. 22
    Doi: http://doi.org/10.1177/2331216518770964
    •
  • Schlittenlacher, J., Turner, RE. and Moore, BCJ., 2018. A Hearing-Model-Based Active-Learning Test for the Determination of Dead Regions. Trends Hear, v. 22
    Doi: http://doi.org/10.1177/2331216518788215
    •

    2017 (No publication date)

  • Afzal, AM., Mussa, HY., Turner, RE., Bender, A. and Glen, RC., 2017 (No publication date). Target Fishing: A Single-Label or Multi-Label Problem? arXiv,
    •

    2017 (Accepted for publication)

  • Turner, RE., Bui, T. and Yan, J., 2017 (Accepted for publication). A Unifying Framework for Gaussian Process Pseudo-Point Approximations using Power Expectation Propagation Journal of Machine Learning Research, v. 18
    •

    2016

  • Alexander, AG., Hensman, J., Turner, RE. and Ghahramani, Z., 2016. On sparse variational methods and the Kullback-Leibler divergence between stochastic processes Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, AISTATS 2016,
    •
  • Gomersall, PA., Turner, RE., Baguley, DM., Deeks, JM., Gockel, HE. and Carlyon, RP., 2016. Perception of stochastic envelopes by normal-hearing and cochlear-implant listeners. Hear Res, v. 333
    Doi: http://doi.org/10.1016/j.heares.2015.12.013
    •
  • Hernández-Lobato, JM., Li, Y., Rowland, M., Hernández-Lobato, D., Bui, TD. and Turner, RE., 2016. Black-Box α-divergence minimization Proceedings of the 33rd International Conference on Machine Learning, v. 48
    •

    2015

  • Gu, S., Ghahramani, Z. and Turner, RE., 2015. Neural adaptive sequential Monte Carlo Advances in Neural Information Processing Systems, v. 2015-January
    •
  • Afzal, AM., Mussa, HY., Turner, RE., Bender, A. and Glen, RC., 2015. A multi-label approach to target prediction taking ligand promiscuity into account. J Cheminform, v. 7
    Doi: http://doi.org/10.1186/s13321-015-0071-9
    •
  • Hernández-Lobato, D., Hernández-Lobato, JM., Li, Y., Bui, T. and Turner, RE., 2015. Stochastic Expectation Propagation for Large Scale Gaussian Process Classification

    • 2014

  • Leong, V., Stone, MA., Turner, RE. and Goswami, U., 2014. A role for amplitude modulation phase relationships in speech rhythm perception. J Acoust Soc Am, v. 136
    Doi: http://doi.org/10.1121/1.4883366
    •

    2013

  • Christensen, HL., Turner, RE., Hill, SI. and Godsill, SJ., 2013. Rebuilding the limit order book: Sequential Bayesian inference on hidden states Quantitative Finance, v. 13
    Doi: http://doi.org/10.1080/14697688.2013.851402
    •

    2012

  • Turner, RE. and Sahani, M., 2012. Decomposing signals into a sum of amplitude and frequency modulated sinusoids using probabilistic inference ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings,
    Doi: http://doi.org/10.1109/ICASSP.2012.6288343
    •

    2011

  • Turner, RE. and Sahani, M., 2011. Demodulation as probabilistic inference IEEE Transactions on Audio, Speech and Language Processing, v. 19
    Doi: http://doi.org/10.1109/TASL.2011.2135852
    •
  • Turner, RE. and Sahani, M., 2011. Probabilistic amplitude and frequency demodulation Advances in Neural Information Processing Systems 24: 25th Annual Conference on Neural Information Processing Systems 2011, NIPS 2011,
    •

    2009

  • Turner, RE., Walters, TC., Monaghan, JJM. and Patterson, RD., 2009. A statistical, formant-pattern model for segregating vowel type and vocal-tract length in developmental formant data J ACOUST SOC AM, v. 125
    Doi: http://doi.org/10.1121/1.3079772
    •
  • Berkes, P., Turner, RE. and Sahani, M., 2009. A Structured Model of Video Reproduces Primary Visual Cortical Organisation PLoS Computational Biology, v. 5
    •

    2007

  • Turner, RE. and Sahani, M., 2007. A Maximum-Likelihood Interpretation for Slow Feature Analysis Neural Computation, v. 19
    Doi: http://doi.org/10.1162/neco.2007.19.4.1022
    •

    2005

  • Smith, DRR., Patterson, RD., Turner, R., Kawahara, H. and Irino, T., 2005. The processing and perception of size information in speech sounds. J Acoust Soc Am, v. 117
    Doi: http://doi.org/10.1121/1.1828637
    •
    Working papers

    2017

  • Nguyen, CV., Li, Y., Bui, TD. and Turner, RE., 2017. Variational Continual Learning
    • Book chapters

    2011

  • Turner, RE. and Sahani, M., 2011. Two problems with variational expectation maximisation for time-series models

    • 2009

  • Lücke, J., Turner, RE., Sahani, M. and Henniges, M., 2009. Occlusive Components Analysis

    • 2006

  • Turner, RE., Al-Hames, MA., Smith, DRR., Kawahara, H., Irino, T. and Patterson, RD., 2006. Vowel normalisation: Time-domain processing of the internal dynamics of speech
    • Professor of Machine Learning
    Departments and institutes: 
    Department of Engineering
    Dr Richard E. Turner

    Affiliations

    Classifications: 
    Academic Staff

    Study at Cambridge

    About the University

    Research at Cambridge