Dependable Neural Networks Through Redundancy, A Comparison of Redundant Architectures

Autor:	Doran, Hans Dermot, Ielpo, Gianluca, Ganz, David, Zapke, Michael
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Hardware Architecture Electrical Engineering and Systems Science - Systems and Control B.8.1 C.1.4 C.3
Druh dokumentu:	Working Paper
Popis:	With edge-AI finding an increasing number of real-world applications, especially in industry, the question of functionally safe applications using AI has begun to be asked. In this body of work, we explore the issue of achieving dependable operation of neural networks. We discuss the issue of dependability in general implementation terms before examining lockstep solutions. We intuit that it is not necessarily a given that two similar neural networks generate results at precisely the same time and that synchronization between the platforms will be required. We perform some preliminary measurements that may support this intuition and introduce some work in implementing lockstep neural network engines. Comment: Presented at the Embedded World Conference 2021, Nuremberg (online). 4 pages, 5 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2108.02565 Zobrazit plný text záznamu View this record from Arxiv