Model and Method for Providing Resilience to Resource-Constrained AI-System

Artificial intelligence technologies are becoming increasingly prevalent in resource-constrained, safety-critical embedded systems. Numerous methods exist to enhance the resilience of AI systems against disruptive influences. However, when resources are limited, ensuring cost-effective resilience be...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Sensors (Basel, Switzerland) Ročník 24; číslo 18; s. 5951
Hlavní autori:	Moskalenko, Viacheslav, Kharchenko, Vyacheslav, Semenov, Serhii
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Switzerland MDPI AG 13.09.2024 MDPI
Predmet:	Adaptation adversarial attack affordable resilience Artificial intelligence Business metrics Comparative analysis concept drift dynamic deep neural networks Edge computing Efficiency Embedded systems fault injection Fault tolerance Methods Neural networks R&D Research & development robustness Ukraine adversarial attack robustness dynamic deep neural networks affordable resilience fault injection concept drift
ISSN:	1424-8220, 1424-8220
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Buďte prvý, kto okomentuje tento záznam!