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

September 2018 Paper

Sep 24, 2018

September paper on 'Co-Creation in Practice: Objectives and Outcomes' by Katharina Greve, Veronica Martinez and Andy Neely

Land of Innovation Forum

Sep 23, 2018

Veronica delivered a presentation and a workshop at the 'Land of Innovation Forum' in Canacintra, Mexico.

Blockchain Results Delivered at Rolls Royce

Sep 20, 2018

Research project 'the impact of digital twins on the product development process' led by Veronica Martinez

Interview with Sander Kuik, Canon – for CSA Industry Day 2018

Sep 11, 2018

In a conversation with Sander Kuik from Canon we asked him about his planned presentation at the CSA Industry Conference on 3 October 2018, his thoughts on the theme of the conference, and his vision of the future.

Webinar 10 September 2018 - Enabling Digital Transformation: An Analysis Framework - by Thayla Zomer, Veronica Martinez and Andy Neely

Sep 10, 2018

In this webinar, Thayla Zomer presented the Alliance May paper on Digital Transformation.

View all news

Upcoming events

Industry Day - 3 October 2018

Oct 03, 2018

Moller Centre, Cambridge

Shift to Services Executive Education Programme

Nov 07, 2018

IfM, Cambridge, UK

Ecosystems Strategy One Day Course

Nov 15, 2018

IfM, Cambridge

Upcoming events