HYPR parallelizes the online learning rule e-prop over sequence segments using associative scans, achieving constant memory, large speedups, and near-BPTT accuracy on several tasks with oscillatory spiking neurons.
Hippo: Recurrent mem- ory with optimal polynomial projections
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networks
HYPR parallelizes the online learning rule e-prop over sequence segments using associative scans, achieving constant memory, large speedups, and near-BPTT accuracy on several tasks with oscillatory spiking neurons.