Tiny Deep Ensemble: Uncertainty Estimation in Edge AI Accelerators via Ensembling Normalization Layers with Shared Weights

arXiv:2405.05286v1 Announce Type: new
Abstract: The applications of artificial intelligence (AI) are rapidly evolving, and they are also commonly used in safety-critical domains, such as autonomous driving and medical diagnosis, where functional safety is paramount. In AI-driven systems, uncertainty estimation allows the user to avoid overconfidence predictions and achieve functional safety. Therefore, the robustness and reliability of model predictions can be improved. However, conventional uncertainty estimation methods, such as the deep ensemble method, impose high computation and, accordingly, hardware (latency …

abstract accelerators ai accelerators ai-driven applications applications of artificial intelligence artificial artificial intelligence arxiv autonomous autonomous driving cs.ai cs.lg diagnosis domains driving edge edge ai ensemble functional intelligence medical normalization safety safety-critical systems type uncertainty via