skip to primary navigationskip to content

Cambridge Service Alliance

developing new understanding and approaches to complex service systems

Studying at Cambridge

 

High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach

last modified Feb 21, 2018 10:36 AM
February Paper on High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach by Tim Pearce, Mohamed Zaki, Alexandra Brintrup, Andy Neely

[Paper]

Deep neural networks (NNs) have caused great excitement due to the step-changes in performance they have delivered in a variety of applications. However, their appeal in industry can be inhibited by an inability to quantify the uncertainty of their predictions. To take a prognostics example, a typical NN might predict that a machine will fail in 60 days. It is unclear from this point prediction whether the machine should be repaired immediately, or whether it can be run for another 59 days. However, if the NN could output a prediction interval (PI) of 45-65 days with 99% probability, timing of a repair could easily be scheduled. In this paper, we develop a method for doing exactly this - the quantification of uncertainty in deep learning using PIs. We derive a method based on the assumption that high-quality PIs should be as narrow as possible, whilst still capturing a given proportion of data. The method is general, applicable to any data-driven task where a continuous value needs to be predicted, and it is important to know the uncertainty of that prediction. Examples include the forecasting of precipitation, energy load, financial metrics, and traffic volume. The method is tested on ten real-world, open-source datasets. The proposed method is shown to outperform current state-of-the-art uncertainty quantification methods, reducing average PI width by around 10%.

RSS Feed Latest news

February 2019 Webinar - Business Ecosystems Mapping

Feb 12, 2019

In this webinar, Florian presents the Alliance January 2019 paper on Business Ecosystems Mapping.

January 2019 Paper

Jan 21, 2019

January 2019 paper on 'Using Business Ecosystems Mapping to Generate new Competitive Value Propositions'

Webinar 14 January

Jan 16, 2019

In this webinar, Tim Pearce discusses his paper on Bayesian Neural Network Ensembles

December 2018 Paper

Dec 19, 2018

December 2018 Paper on 'Bayesian Neural Network Ensembles'

Webinar 10 December 2018

Dec 14, 2018

Webinar on Service Business Model Innovation: The Digital Twin Technology by Veronica Martinez, Audrey Ouyang, Andy Neely, Caroline Burstall and Dav Bisessar

View all news

Upcoming events

Shift to Services Executive Education Programme

May 14, 2019

IfM, Cambridge, UK

Upcoming events