Examining redundancy in the context of safe machine learning

Please use this identifier to cite or link to this item: https://doi.org/10.21256/zhaw-20248

Publication type:	Conference paper
Type of review:	Peer review (abstract)
Title:	Examining redundancy in the context of safe machine learning
Authors:	Doran, Hans Dermot Reif, Monika Ulrike
et. al:	No
DOI:	10.21256/zhaw-20248
Proceedings:	Proceedings of the Forum for Safety & Security 2020
Conference details:	Forum Safety & Security, 23-24 June 2020, virtueller Event
Issue Date:	23-Jun-2020
Publisher / Ed. Institution:	WEKA
Language:	English
Subjects:	Functional safety; Dependability; Redundancy; Machine learning
Subject (DDC):	004: Computer science
Abstract:	This paper describes a set of experiments with neural network classifiers on the MNIST database of digits. The purpose is to investigate naïve implementations of redundant architectures as a first step towards safe and dependable machine learning. We report on a set of measurements using the MNIST database which ultimately serve to underline the expected difficulties in using NN classifiers in safe and dependable systems.
URI:	https://arxiv.org/abs/2007.01900 https://digitalcollection.zhaw.ch/handle/11475/20248
Fulltext version:	Published version
License (according to publishing contract):	Licence according to publishing contract
Departement:	School of Engineering
Organisational Unit:	Institute of Applied Mathematics and Physics (IAMP) Institute of Embedded Systems (InES)
Appears in collections:	Publikationen School of Engineering

Files in This Item:

File	Description	Size	Format
2020_Doran-Reif_Redundancy-Machine-Learning_FSS20-Paper.pdf		445.39 kB	Adobe PDF	View/Open