Selected talks

  • Invited talks.
  • Conference/workshop talks.
  • Other.


  • "Deep Gaussian Processes - Test of Time Award."
    AISTATS, Valencia, Apr. 2023 [Slides]

  • "Podcast Recommendations and Search Query suggestions using Graph neural networks at Spotify."
    Pinterest, Dec. 2022

  • "Kickstart Your Career in Data - Panel."
    Zindi.africa & Pan African Women Empowerment Network, Oct. 2022

  • "Podcast Recommendations and Search Query suggestions using Graph neural networks at Spotify."
    Stanford Graph Learning Workshop, Stanford University, Sep. 2022. [Video]

  • "Working with Data in Industrial ML Applications."
    Univ. of Sapienza, Rome, 27 and 28 April 2022 [Slides]

  • "The role of uncertainty in machine learning."
    Cambridge Science Accelerator Winter School, 02/02/2021 [Web] [Slides]

  • "Deep Learning in the Function space."
    NeurIPS 2020 Nairobi Meetup, 10/12/2020 [PDF] [Video]

  • "Deep Learning practical considerations."
    Data Science Africa - Kampala (Virtual), 24/07/2020 [PDF] [Notebook] [Video]

  • "Fast Computation with Linearized Neural Networks for Domain Adaptation."
    Microsoft Research & Univ. Cambridge Meetup, 28/02/2020 [PDF]

  • "From GP to deep learning and from deep learning to GP."
    ATI/Aalto Workshop on Deep Structures, Helsinki, 19/12/2019 [PDF]

  • "Deep and Multi-fidelity learning with Gaussian processes."
    Advances in Data Science Seminar Series, Univ. of Manchester, 15/10/2019 [PDF] [GP tutorial]

  • "Deep and Multi-fidelity learning with Gaussian processes."
    Uncertainty Propagation in Composite Models, Munich, 11/10/2019

  • "Deep and Multi-fidelity learning with Gaussian processes."
    Alan Turing Institute workshop on Uncertainty Quantification, 06/08/2019 [PDF]

  • "Deep learning, probability and uncertainty."
    Univ. of Warwick CS Colloquium, 06/06/2019 [PDF]

  • "Introduction to deep transfer learning with Xfer."
    University of Leeds, 08/03/2019 [PDF] [notebook]

  • "Deep transfer learning with Xfer."
    MXnet Deep Learning meetup, London, 06/03/2019 [PDF] [notebook]

  • "Introduction to deep learning."
    Royal Statistical Society, London, 13/12/2018 [PDF] [notebook]

  • [Blog post]
    "Xfer: an open-source library for neural network transfer learning." [LINK]

  • "Inverse Reinforcement Learning with Deep Gaussian processes."
    Prowler.io, 03/07/2018

  • "Probabilistic and Bayesian deep learning."
    Univ. of Sheffield, 19/03/2018

  • "Variational inference in Deep Gaussian processes."
    Keynote at NIPS workshop on approximate Bayesian inference, Long Beach, USA, 08/12/2017 [PDF]

  • "Probability & uncertainty in deep learning."
    Deep Learning summit, London, 21/09/2017 [PDF]

  • "Introduction to Deep Learning."
    Data Science in Africa, Arusha, Tanzania, 19/06/2017 [PDF] [notebook]

  • "Probabilistic and Bayesian deep learning."
    University of Bristol, UK, 17/05/2017

  • "Variational constraints for training deep and recurrent Gaussian processes."
    Harvard University, USA, 23/02/2016

  • "Representation and deep learning with Bayesian non-parametric models."
    Microsoft Research MA, USA, 22/02/2016

  • "Latent variable and deep modeling with Gaussian processes; applications to system identification."
    Brown University, USA, 17/02/2016 [PDF]

  • "Gaussian processes for data-driven modeling and uncertainty quantification: a hands-on tutorial."
    Brown University, USA, 16/02/2016 [PDF] [Jupyter notebook]

  • "System identification and control with (deep) Gaussian processes."
    MIT, USA, 11/02/2016 [PDF]

  • "Representation and deep learning with Bayesian non-parametric models"
    Athens University of Economics and Business, Greece, 14/10/2015 [PDF]

  • "Bayesian latent variable modelling with GPs"
    Gaussian Process Summer School, Sheffield, UK, 14/09/2015 [PDF] [Video]

  • "A top-down approach for a synthetic autobiographical memory system"
    4th International Conference on Biomimetic and Biohybrid Systems (Living Machines), Barcelona, 31/07/2015 [PDF]

  • "Deep Gaussian Processes and Variational Propagation of Uncertainty"
    Department of Engineering, University of Cambridge, UK, 29/06/2015 [PDF]

  • "Probabilistic Models for Learning Data Representations"
    IBM Research, Nairobi, Kenya, 23/06/2015 [PDF]

  • "Dimensionality Reduction and Latent Variable Modelling"
    Data Science School and Data Science Workshop in Africa, Nyeri, Kenya, 17/06/2015 [PDF]

  • "Deep non-parametric learning with Gaussian processes"
    School of Computing Science, Glasgow, Scotland, 10/06/2015 [PDF]

  • "Deep probabilistic modelling with deep GPs"
    First Workshop on Deep Probabilistic Models, Sheffield, 02/10/2014 [PDF]

  • "Feature representations with Deep Gaussian processes"
    Feature Extraction with Gaussian Processes Workshop, Sheffield, 18/09/2014 [PDF]

  • "Deep Gaussian processes"
    Deep Learning meetup, London, 24/06/2014. [PDF] [video]

  • "Deep Gaussian processes"
    Imperial College, London, 23/06/2014. [Link]

  • "Modeling and consolidating complex data with Gaussian process models"
    ICS-FORTH, Heraklion, Greece, 10/06/2014. [PDF]

  • "Deep Gaussian processes."
    University of Washington, USA, 28/01/2013.

  • "Modeling complex data with deep Gaussian processes."
    Microsoft Research, Redmond, USA, 23/01/2013.

  • "Modeling dynamical and multi-modal computer vision data via non-linear probabilistic dimensionality reduction."
    University of Surrey, UK, 14/06/2012. [PDF]

  • "Tutorial on Gaussian Processes and the Gaussian Process Latent Variable Model (& discussion on the GPLVM tech. report by Prof. N. Lawrence, ’06)."
    University of Surrey, UK, 13/06/2012. [PDF]

  • "Variational Gaussian process latent variable models for high dimensional image data."
    The Rank Prize Machine Learning and Vision Symposium, Cumbria, UK, 2012 [PDF]

  • "Non-linear probabilistic dimensionality reduction for dynamical and multi-modal vision datasets."
    The School of Computer Science and Communication, KTH, Stockholm, Sweden, 2012. [PDF]

  • "Manifold Relevance Determination."
    ICML 2012. [PDF] [Video]



 

 

 

 

 

*Thanks to J. Hensman & N. Fusi for lending me their nice latex templates!