Dependable Neural Networks Through Redundancy, A Comparison of Redundant Architectures
This work addresses the need for functionally safe AI in industrial edge applications, but it appears incremental as it builds on existing redundancy concepts with preliminary findings.
The paper tackles the problem of achieving dependable operation of neural networks for edge-AI applications by exploring redundant architectures, specifically lockstep solutions, and presents preliminary measurements and implementation work to address synchronization issues.
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.