Search

Machine learning

Learn more

Transforming medicine through AI-enabled healthcare pathways

Monday 03 Jun 2019

Time: 18:00 - 20:00

Jem Rashbass Mihaela van der Schaar

Data-centric materials science and engineering

Tuesday 14 May 2019 - Wednesday 15 May 2019

Time: 09:00 - 17:00

Tony Hey Philip Withers Louise Wright Catherine Powell Chris Taylor Keith Butler Prof. Timothy Cootes Dr. Luke Mason Dr. Robin Pinning Prof. Vassil Alexandrov Dr. Hector Basoalto Joshua Franz Einsle Mark Girolami Din-Houn Lau Andrew Duncan Pranay Seshadri Tim Dodwell Patrick Rubin-Delanchy

Mathematics of data

Wednesday 29 May 2019 - Friday 31 May 2019

Time: 10:00 - 17:00

Turing Lecture: Machine learning and big scientific data benchmarks

Tuesday 02 Oct 2018

Time: 18:00 - 19:30

Tony Hey

Beyond tech: Machine learning in science & policy

Tuesday 22 May 2018

Time: 14:00 - 15:00

Detecting semantic shift in large corpora by exploiting temporal random indexing

Monday 23 Apr 2018

Time: 11:00 - 12:30

Understanding Multimodal Data at Scale

Monday 30 Nov 2015 - Tuesday 01 Dec 2015

Time: 17:38

Turing data science class: Advanced machine learning

Monday 05 Mar 2018

Time: 13:30 - 15:30

Projects

Molecular structure from images under physical constraints

Using machine learning and high resolution imaging to determine biomolecular structure and dynamics

Statistical machine learning for randomised clinical trials (MRC CTU)

Developing and applying machine learning methods to improve the design, conduct and analyses of clinical trials

Identifying potential disease causing variants in genetic data

Developing an algorithm to identify disease causing variants in protein-coding regions of genes

Machine learning and large cryogenic electron microscopy data sets

Applying machine learning techniques to identify interacting protein molecules in large cryogenic electron microscopy (cryo-EM) data

Integrating information visualisation with machine learning

Integrating interactive data and information visualisation with machine learning technologies for learning for large datasets

Scalable regression: Tools and techniques

Developing techniques for regression models to scale at large data volumes, incorporating regression model power into big data analytics engines

Publications and software

Research publications

Learning Bijective Feature Maps for Linear ICA

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

Camuto, A., Willetts, M., Paige, B., Holmes, C., Roberts, S., (2020) Learning Bijective Feature Maps for Linear ICA

Research publications

Improving VAEs’ Robustness to Adversarial Attack

Variational autoencoders (VAEs) have recently been shown to be vulnerable to adversarial attacks, wherein...

Willetts, M., Camuto, A., Rainforth, T., Roberts, S., Holmes, C., (2021) Improving VAEs’ Robustness to Adversarial Attack. International Conference of Learning Representations (ICLR)

Research publications

Explicit Regularisation in Gaussian Noise Injections

We study the regularisation induced in neural networks by Gaussian noise injections (GNIs). Though...

Camuto, A., Willetts, M., Şimşekli, U., Roberts, S., & Holmes, C. (2020). Explicit Regularisation in Gaussian Noise Injections. NeurIPS

Research publications

Disentangling to Cluster

Gaussian Mixture Variational Ladder Autoencoders

Willetts, M., Roberts, S., Holmes, C. (2019) Disentangling to Cluster: Gaussian Mixture Variational Ladder Autoencoders. NeurIPS Bayesian Deep Learning Workshop 2019

Research publications

Data Study Group Final Report: Agile Datum

Automating the evaluation of local government planning applications

Data Study Group team. (2021, March 10). Data Study Group Final Report: Agile Datum. Zenodo. https://doi.org/10.5281/zenodo.5729594

Research publications

Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks

While much attention has been given to the problem of estimating the effect of...

Bica, I., Jordon, J., & van der Schaar, M. (2020). Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks. arXiv preprint arXiv:2002.12326.

Research publications

Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders

The estimation of treatment effects is a pervasive problem in medicine. Existing methods for...

Bica, I., Alaa, A. M., & van der Schaar, M. (2020). Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders. International Conference on Machine Learning (ICML) 2020.

Research publications

A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating

A new approach in stochastic optimization via the use of stochastic gradient Langevin dynamics...

A fully data-driven approach to minimizing CVaR for portfolio of assets via SGLD with discontinuous updating. Sabanis, Sotirios; Zhang, Ying. arXiv:2007.01672 [q-fin.PM]

Research publications

Taming neural networks with TUSLA: Non-convex learning via adaptive stochastic gradient Langevin algorithms

Artificial neural networks (ANNs) are typically highly nonlinear systems which are finely tuned via...

Taming neural networks with TUSLA : Non-convex learning via adaptive stochastic gradient Langevin algorithms. Lovas, Attila; Lytras, Iosif ; Rásonyi, Miklós ; Sabanis, Sotirios. arXiv:2006.14514 [cs.LG]