Towards Safe Spiking Neural Networks for Classification
-
- Englisch ausgewählt
Fr. 36.90
inkl. gesetzl. MwSt.,
Beschreibung
Produktdetails
Einband
Taschenbuch
Erscheinungsdatum
27.04.2026
Abbildungen
20
Verlag
TUDpressSeitenzahl
150
Maße (B/H)
14.8/20 cm
Gewicht
235 g
Sprache
Englisch
ISBN
978-3-95908-748-3
Artificial intelligence increasingly influences daily decision-making, yet the safety of neural networks – particularly Spiking Neural Networks (SNNs) – remains a critical challenge. This dissertation enhances SNN safety in time-series classification through selective prediction, where high-uncertainty inputs are rejected to reduce errors. Two novel methods are introduced: a loss-based monitor that identifies risky inputs without relying on output probabilities, and a time-aware Conformal Prediction (CP) approach that corrects temporal uncertainties overlooked by standard CP. These methods are benchmarked on four public datasets and Infineon’s radar-based gesture data against state-of-the-art baselines, namely Evidential Deep Learning (EDL) and Neural Network Ensembles (NNEs).In addition to fixed-length evaluations, the research addresses real-time scenarios with streaming data, deploying SNNs via sliding windows and stateful architectures, where rejections act as safety interventions. Custom metrics are developed to better evaluate performance in this dynamic setting. Results reveal stateful deployment enables to catch more errors than sliding windows. EDL excels in accuracy-safety trade-offs, while CP delivers safety improvements with minimal computational overhead, offering scalable solutions for real-world SNN applications.
Noch keine Bewertungen vorhanden
Verfassen Sie die erste Bewertung zu diesem Artikel
Helfen Sie anderen Kundinnen und Kunden durch Ihre Meinung.