Safety in the Face of Unknown Unknowns: Algorithm Fusion in Data-driven Engineering Systems

Most current machine learning algorithms make highly confident yet incorrect classifications when faced with unexpected test samples from an unknown distribution different from training; such epistemic uncertainty (unknown unknowns) can have catastrophic safety implications. In this conceptual paper...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 8162 - 8166
Main Authors: Kshetry, Nina, Varshney, Lav R.
Format: Conference Proceeding
Language:English
Published: IEEE 01.05.2019
Subjects:
AI safety
algorithm fusion
Data models
epistemic uncertainty
Knowledge engineering
metacognition
Safety
Sensors
Training
Uncertainty
Wastewater
wastewater treatment
ISSN:2379-190X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Most current machine learning algorithms make highly confident yet incorrect classifications when faced with unexpected test samples from an unknown distribution different from training; such epistemic uncertainty (unknown unknowns) can have catastrophic safety implications. In this conceptual paper, we propose a method to leverage engineering science knowledge to control epistemic uncertainty and maintain decision safety. The basic idea is an algorithm fusion approach that combines data-driven learned models with physical system knowledge, to operate between the extremes of purely data-driven classifiers and purely engineering science rules. This facilitates the safe operation of data-driven engineering systems, such as wastewater treatment plants.
ISSN:2379-190X
DOI:10.1109/ICASSP.2019.8683392