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

Webinar 12 November 2018 - Co-Creation in Practice: Objectives and Outcomes

Nov 14, 2018

In this webinar, Katharina Greve presents the Alliance September Paper on Co-Creation in Practice.

New EPSRC Doctoral Studentship Opportunity

Nov 09, 2018

New EPSRC Doctoral Studentship Opportunity on Digital technology in the service design and lifecycle with Rolls Royce

Do not fall prey to business ecosystem failure

Oct 26, 2018

There are many reasons why great manufacturing innovations that should have succeeded end up on the scrap heap. Dr Florian Urmetzer explains that an often-overlooked but very common reason is failure to see the blind spots in your business ecosystem.

CEMEX Workshop

Oct 26, 2018

Blockchain Prototype: Scope and Analysis for CEMEX

New book published: Exploring Service Science

Oct 25, 2018

9th International Conference, IESS 2018, Karlsruhe, Germany, September 19–21, 2018, Proceedings

View all news

Upcoming events

Ecosystems Strategy One Day Course

Feb 05, 2019

IfM, Cambridge

Upcoming events