Publication type: | Conference other |
Type of review: | Peer review (abstract) |
Title: | Making AI architectures and models applicable for functional safety |
Authors: | Doran, Hans Dermot |
et. al: | No |
Proceedings: | Proceedings of the Forum Safety & Security 2022 |
Conference details: | Forum Safety & Security, Landshut, Germany, 21-22 September 2022 |
Issue Date: | Sep-2022 |
Language: | English |
Subjects: | Functional safety; Artificial intelligence; Dependability; Neural network |
Subject (DDC): | 006: Special computer methods |
Abstract: | In this presentation we review the latest state-of-the-art in safety and neural network related technologies with a specific focus on those that are applicable to industry. We begin by considering the dependability of operations on the hardware level in AI architectures and show what techniques are used both in industry and suggested in research and appear viable for actual implementation. We then look at the monitoring approach where some bounding function is applied on the output of either the entire model or the results of individual calculations. We then describe more complex approaches where the model itself is analysed for potentially vulnerable calculations and conclusions drawn as the best way to ensure the dependability of operation. In all these cases we focus on the practicality of the potential solutions and, where possible, estimate the resources required. We conclude with a suggestion of trends with application potential for industry in general. |
URI: | https://digitalcollection.zhaw.ch/handle/11475/26905 |
Fulltext version: | Published version |
License (according to publishing contract): | Licence according to publishing contract |
Departement: | School of Engineering |
Organisational Unit: | Institute of Embedded Systems (InES) |
Appears in collections: | Publikationen School of Engineering |
Files in This Item:
There are no files associated with this item.
Show full item record
Doran, H. D. (2022, September). Making AI architectures and models applicable for functional safety. Proceedings of the Forum Safety & Security 2022.
Doran, H.D. (2022) ‘Making AI architectures and models applicable for functional safety’, in Proceedings of the Forum Safety & Security 2022.
H. D. Doran, “Making AI architectures and models applicable for functional safety,” in Proceedings of the Forum Safety & Security 2022, Sep. 2022.
DORAN, Hans Dermot, 2022. Making AI architectures and models applicable for functional safety. In: Proceedings of the Forum Safety & Security 2022. Conference presentation. September 2022
Doran, Hans Dermot. 2022. “Making AI Architectures and Models Applicable for Functional Safety.” Conference presentation. In Proceedings of the Forum Safety & Security 2022.
Doran, Hans Dermot. “Making AI Architectures and Models Applicable for Functional Safety.” Proceedings of the Forum Safety & Security 2022, 2022.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.