An end-to-end spiking encoder-decoder network achieves 92.05/87.04/86.51 AP on KITTI BEV detection with a claimed 3.33x synaptic energy reduction versus an equivalent CNN.
Training spiking neural networks using lessons from deep learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
verdicts
UNVERDICTED 5representative citing papers
Memristive networks exhibit biological-like population spiking and nonlinear resonance maximized when input frequency matches the network's intrinsic timescale, with optimal computation frequency just before resonance onset.
SPIKER-LL extends the open-source Spiker+ SNN accelerator with microarchitectural support for the STSF local learning rule, delivering up to 93% accuracy, sub-millisecond latency, and under 0.1 mJ per inference on MNIST variants while remaining DSP-free.
SNNF uses an event-based binary image and single-layer SNN to achieve 0.89 AUC in distinguishing signal from noise in DVS while using only 11-40% of the resources of prior filters.
A neuromorphic edge system using event vision and sparse SNNs on Loihi 2 achieves up to 84% F1 score at 90 mW for privacy-preserving fall detection.
citing papers explorer
-
Neuromorphic LiDAR-based Bird's Eye View Object Detection using Energy-efficient Spiking Neural Networks
An end-to-end spiking encoder-decoder network achieves 92.05/87.04/86.51 AP on KITTI BEV detection with a claimed 3.33x synaptic energy reduction versus an equivalent CNN.
-
Intrinsic Neuro-Synaptic Spiking Dynamics and Resonance in Memristive Networks
Memristive networks exhibit biological-like population spiking and nonlinear resonance maximized when input frequency matches the network's intrinsic timescale, with optimal computation frequency just before resonance onset.
-
Spiker-LL: An Energy-Efficient FPGA Accelerator Enabling Adaptive Local Learning in Spiking Neural Networks
SPIKER-LL extends the open-source Spiker+ SNN accelerator with microarchitectural support for the STSF local learning rule, delivering up to 93% accuracy, sub-millisecond latency, and under 0.1 mJ per inference on MNIST variants while remaining DSP-free.
-
SNNF: An SNN-based Near-Sensor Noise Filter for Dynamic Vision Sensors
SNNF uses an event-based binary image and single-layer SNN to achieve 0.89 AUC in distinguishing signal from noise in DVS while using only 11-40% of the resources of prior filters.
-
Privacy-preserving fall detection at the edge using Sony IMX636 event-based vision sensor and Intel Loihi 2 neuromorphic processor
A neuromorphic edge system using event vision and sparse SNNs on Loihi 2 achieves up to 84% F1 score at 90 mW for privacy-preserving fall detection.