Knowing when to stop: Delay-adaptive spiking neural network classifiers with reliability guarantees
Spiking neural networks (SNNs) process time-series data via internal event-driven neural
dynamics. The energy consumption of an SNN depends on the number of spikes exchanged …
dynamics. The energy consumption of an SNN depends on the number of spikes exchanged …
Average-Over-Time Spiking Neural Networks for Uncertainty Estimation in Regression
Uncertainty estimation is a standard tool to quantify the reliability of modern deep learning
models, and crucial for many real-world applications. However, efficient uncertainty …
models, and crucial for many real-world applications. However, efficient uncertainty …
[PDF][PDF] Reliable Neuromorphic Computing and Wireless Communication
J Chen, B Rajendran - 2024 - kclpure.kcl.ac.uk
Artificial Intelligence (AI) and wireless communications represent two pivotal technologies
that have transformed numerous facets of modern society. AI techniques, ranging from …
that have transformed numerous facets of modern society. AI techniques, ranging from …
A discussion of migration of common neural network regularization methods on SNNs
SNN models offer notable advantages in terms of memory efficiency and energy
consumption when compared to traditional artificial neural network models. However, their …
consumption when compared to traditional artificial neural network models. However, their …
[PDF][PDF] Deep Learning for Eye Disease Detection with Confidence Estimation and Explainable AI
A MAYOWA-MAJARO - 2024 - irejournals.com
This research made progress on not only identifying valid deep learning models that can
detect various eye diseases but also making the diagnosis process easier for physicians …
detect various eye diseases but also making the diagnosis process easier for physicians …