• search hit 7 of 36
Back to Result List

Certainty Groups: A Practical Approach to Distinguish Confidence Levels in Neural Networks

  • Machine Learning (ML), in particular classification with deep neural nets, can be applied to a variety of industrial tasks. It can augment established methods for controlling manufacturing processes such as statistical process control (SPC) to detect non-obvious patterns in high-dimensional input data. However, due to the widespread issue of model miscalibration in neural networks, there is a need for estimating the predictive uncertainty of these models. Many established approaches for uncertainty estimation output scores that are difficult to put into actionable insight. We therefore introduce the concept of certainty groups which distinguish the predictions of a neural network into the normal group and the certainty group. The certainty group contains only predictions with a very high accuracy that can be set up to 100%. We present an approach to compute these certainty groups and demonstrate our approach on two datasets from a PHM setting.

Download full text files

Export metadata

Additional Services

Search Google Scholar
Metadaten
Author:Lukas Lodes, Alexander SchiendorferORCiD
Language:English
Document Type:Conference Paper
Conference:PHME 2022: 7th European Conference of the Prognostics and Health Management Society 2022, Turin (Italy), 06.-08.07.2022
Year of first Publication:2022
published in (English):Proceedings of the European Conference of the PHM Society 2022
Editor(s):Phuc Do, Gabriel Michau, Cordelia Ezhilarasu
Publisher:PHM Society
Place of publication:State College
ISBN:978-1-936263-36-3
First Page:294
Last Page:305
Review:peer-review
Open Access:ja
Tag:classification; estimaton; machine Learning; neural network; uncertainty
URN:urn:nbn:de:bvb:573-31307
Related Identifier:https://doi.org/10.36001/phme.2022.v7i1.3331
Faculties / Institutes / Organizations:Fakultät Wirtschaftsingenieurwesen
AImotion Bavaria
Licence (German):License Logo Creative Commons BY 3.0 US
Release Date:2023/02/24