analiza aiqbench
This research introduces BLADE, a framework that optimizes the boundary between Spiking Neural Networks (SNN) and Artificial Neural Networks (ANNs) by explicitly incorporating hardware reliability into the design process. By identifying and protecting specific floating-point bits prone to catastrophic failures, the method significantly reduces energy consumption while maintaining high accuracy for safety-critical edge AI applications. The work represents a crucial step toward deploying robust hybrid neural architectures in real-world environments where hardware faults are a tangible concern.
BLADE: ReliaBle Dynamic Hardware-Aware SNN-ANN Boundary SeLection for Event-BAseD Object DEtection
arXiv:2609.17562v1 Announce Type: cross Abstract: Hybrid Spiking Neural Network (SNN)-Artificial Neural Network (ANN) architectures combine the energy efficiency of SNNs with the superior detection accuracy of ANNs for event-based object detection. Existing hybrid SNN--ANN networks, however, employ static inference and select the SNN-ANN boundary primarily according to accuracy and energy consumption, without considering dynamic inference or reliability. This paper presents BLADE, the first reliability-aware boundary selection methodology for dynamic hybrid SNN-ANN networks with ANN early exit. The proposed framework jointly optimizes the SNN-ANN boundary and ANN early-exit configuration according to reliability, detection accuracy, execution time, and energy consumption, while incorporating reliability through hierarchical statistical fault injection during design-space exploration. Experimental evaluation on an event-based object detector achieves an mAP 0.5 of 0.691 while reducing the inference compute energy to 15.82~mJ when the ANN early exit fires. Reliability analysis identifies the most significant floating-point exponent bit as the dominant source of catastrophic failures, producing significant-or-worse accuracy degradation in 58.8% of its fault injections. Protecting this single bit with approximately 3% storage overhead eliminates catastrophic failures across the evaluated realistic technology fault rates. Furthermore, increasing the proportion of SNN computation improves fault tolerance, with the fully SNN configuration achieving a reliability retention of 0.965 under aggressive fault conditions. The results demonstrate that jointly optimizing reliability, accuracy, execution time, and energy consumption enables more dependable deployment of dynamic hybrid SNN--ANN systems for safety-critical edge AI applications.
Abstract:Hybrid Spiking Neural Network (SNN)-Artificial Neural Network (ANN) architectures combine the energy efficiency of SNNs with the superior detection accuracy of ANNs for event-based object detection. Existing hybrid SNN--ANN networks, however, employ static inference and select the SNN-ANN boundary primarily according to accuracy and energy consumption, without considering dynamic inference or reliability. This paper presents BLADE, the first reliability-aware boundary selection methodology for dynamic hybrid SNN-ANN networks with ANN early exit. The proposed framework jointly optimizes the SNN-ANN boundary and ANN early-exit configuration according to reliability, detection accuracy, execution time, and energy consumption, while incorporating reliability through hierarchical statistical fault injection during design-space exploration. Experimental evaluation on an event-based object detector achieves an mAP 0.5 of 0.691 while reducing the inference compute energy to 15.82~mJ when the ANN early exit fires. Reliability analysis identifies the most significant floating-point exponent bit as the dominant source of catastrophic failures, producing significant-or-worse accuracy degradation in 58.8% of its fault injections. Protecting this single bit with approximately 3% storage overhead eliminates catastrophic failures across the evaluated realistic technology fault rates. Furthermore, increasing the proportion of SNN computation improves fault tolerance, with the fully SNN configuration achieving a reliability retention of 0.965 under aggressive fault conditions. The results demonstrate that jointly optimizing reliability, accuracy, execution time, and energy consumption enables more dependable deployment of dynamic hybrid SNN--ANN systems for safety-critical edge AI applications.
Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Hardware Architecture (cs.AR); Distributed, Parallel, and Cluster Computing (cs.DC); Emerging Technologies (cs.ET); Machine Learning (cs.LG)
arXiv:2609.17562 [cs.NE]
(or arXiv:2609.17562v1 [cs.NE] for this version)
Text integral sub licența deschisă a publicației · 259 cuvinte
Subiecte conexe
Amazon SageMaker Inference: 2026 year-to-date launches in review
AWS · 18 sept. 2026
Maximizing AI Factory Performance per Watt with NVIDIA DSX MaxLPS
NVIDIA · 24 aug. 2026
A Practical Guide to GPU-Initiated Communication for Molecular Dynamics at Scale
NVIDIA · 9 iul. 2026
Problems of Proliferation
LessWrong · 29 sept. 2026