VS-GNO delivers 0.71-1.04% reconstruction error at 15-24.5% spiking rates versus 0.4% for a non-spiking baseline in sparse-to-dense virtual sensing.
Eshraghian, Max Ward, Emre O
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5representative citing papers
A recurrent SNN with heterogeneous synaptic delays (D=41) achieves perfect F1=1.0 recall of 16 arbitrary spike patterns on a synthetic benchmark by representing them as chains of overlapping spiking motifs.
SupraSNN introduces a superscalar-inspired SNN accelerator with decoupled synapse and neuron units, multi-cast/merge trees, and partitioning/scheduling that reports 47.6% lower latency and 5.6x better energy efficiency than prior FPGA SNN designs on MNIST and SHD tasks.
QIF neurons outperform LIF neurons in spike-based gradient descent training of spiking neural networks by avoiding discontinuities that fragment the loss landscape.
Spike sparsity in VS-WNO does not reduce latency or energy on Jetson Orin Nano because the runtime executes dense work regardless of spike activity.
citing papers explorer
-
Neuroscience Inspired Graph Operators Towards Edge-Deployable Virtual Sensing for Irregular Geometries
VS-GNO delivers 0.71-1.04% reconstruction error at 15-24.5% spiking rates versus 0.4% for a non-spiking baseline in sparse-to-dense virtual sensing.
-
Working Memory in a Recurrent Spiking Neural Networks With Heterogeneous Synaptic Delays
A recurrent SNN with heterogeneous synaptic delays (D=41) achieves perfect F1=1.0 recall of 16 arbitrary spike patterns on a synthetic benchmark by representing them as chains of overlapping spiking motifs.
-
SupraSNN: Exploiting Synapse-Level Parallelism in Spiking Neural Network Accelerators through Co-Optimized Mapping and Scheduling
SupraSNN introduces a superscalar-inspired SNN accelerator with decoupled synapse and neuron units, multi-cast/merge trees, and partitioning/scheduling that reports 47.6% lower latency and 5.6x better energy efficiency than prior FPGA SNN designs on MNIST and SHD tasks.
-
Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent
QIF neurons outperform LIF neurons in spike-based gradient descent training of spiking neural networks by avoiding discontinuities that fragment the loss landscape.
-
When Spike Sparsity Does Not Translate to Deployed Cost: VS-WNO on Jetson Orin Nano
Spike sparsity in VS-WNO does not reduce latency or energy on Jetson Orin Nano because the runtime executes dense work regardless of spike activity.