skip to primary navigationskip to content

Cambridge Service Alliance

developing new understanding and approaches to complex service systems

Studying at Cambridge

 

Webinar - High-Quality Prediction Intervals for Deep Learning

last modified Jun 11, 2018 09:51 PM
11 June 2018 - High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach - by Tim Pearce, Mohamed Zaki, Alexandra Brintrup, Andy Neely

In this webinar, Tim discusses the February Alliance 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%.

Webinar I Presentation

RSS Feed Latest news

New Paper - Digital transformation: harnessing digital technologies for the next generation of services

Jun 21, 2019

Check out our recent commentary paper published at the Journal of Services Marketing

The future of digital services and platforms

May 23, 2019

Cambridge Service Alliance Community of Interest Meeting - April 2019

New Paper: Servitization: A contemporary thematic review of four major research streams

May 21, 2019

This study identifies the key themes and research priorities in servitization literature over thirteen years from 2005 and 2017, based on four major research streams (general management, marketing, operations, and service management).

New paper - Redistributed Manufacturing and the Impact of Big Data: A Consumer Goods Perspective

May 21, 2019

This paper builds a conceptual framework to explore whether big data combined with new manufacturing technologies can facilitate redistributed manufacturing (RDM).

HCL joins the Cambridge Service Alliance

Apr 23, 2019

HCL joined the Cambridge Service Alliance as a strategic digital services partner.

View all news