CLP-SNN matches replay-based accuracy rehearsal-free on OpenLORIS few-shot continual learning and achieves 113x lower latency plus 6600x lower energy on Loihi 2 than edge-GPU baselines through algorithmic efficiency and neuromorphic hardware co-design.
Cambridge University Press
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Recurrent networks built from tunable expressive neurons reveal scaling laws with an optimal parameter split that shifts toward higher per-neuron complexity at larger scales.
citing papers explorer
-
Online Continual Learning on Intel Loihi 2 via a Co-designed Spiking Neural Network
CLP-SNN matches replay-based accuracy rehearsal-free on OpenLORIS few-shot continual learning and achieves 113x lower latency plus 6600x lower energy on Loihi 2 than edge-GPU baselines through algorithmic efficiency and neuromorphic hardware co-design.
-
Scaling Laws and Tradeoffs in Recurrent Networks of Expressive Neurons
Recurrent networks built from tunable expressive neurons reveal scaling laws with an optimal parameter split that shifts toward higher per-neuron complexity at larger scales.