A quantized spiking Q-network deployed on SpiNNaker2 matches a GPU on CartPole and Acrobot while using 24x to 32x less energy per episode.
Language modeling on a spinnaker2 neuromorphic chip,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Hardware-Aware Fine-Tuning of Spiking Q-Networks on the SpiNNaker2 Neuromorphic Platform
A quantized spiking Q-network deployed on SpiNNaker2 matches a GPU on CartPole and Acrobot while using 24x to 32x less energy per episode.