skip to content

Cambridge Service Alliance

At the forefront of service transformation in the digital era
 
Neural Networks for the quantification of predictive uncertainty

Tim Pearce will be attending the 35th International Conference on Machine Learning (ICML 2018). Tim is also attending a workshop, part of the conference, and presenting his work on 'Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Reinforcement Learning'.

Tim will be attending the 35th International Conference on Machine Learning (ICML 2018) and presenting his work on 'Bayesian Inference with Anchored Ensembles of Neural Networks, and Application to Reinforcement Learning'. The use of ensembles of neural networks (NNs) for the quantification of predictive uncertainty is widespread. However, the current justification is intuitive rather than analytical. This work proposes one minor modification to the normal ensembling methodology, which we prove allows the ensemble to perform Bayesian inference, hence converging to the corresponding Gaussian Process as both the total number of NNs, and the size of each, tend to infinity. This working paper provides early-stage results in a reinforcement learning setting, analysing the practicality of the technique for an ensemble of small, finite number. Using the uncertainty estimates they produce to govern the exploration-exploitation process results in steadier, more stable learning.

Cambridge Service Alliance

Welcome to the Cambridge Service Alliance…

  • A unique global alliance between the University of Cambridge and some of the world’s leading businesses.

  • Help organisations to address the challenges they will face in the next three to five years, through rigorous research, practical tools, insights and education programmes.

  • Learn how other innovative organisations are developing new services through our events

  • Since its inception in 2010 industrial partners have included BAE Systems, Caterpillar, GEA, IBM, Pearson, Zoetis, CEMEX, HCLTech and Bouygues


CSA News

Lastest News.....