An Expectation-Propagation framework trains spiking neural networks with mini-batches, supporting discrete or continuous weights and deterministic or stochastic spiking, and returns approximate posterior uncertainties.
Memory and information processing in neuromorphic systems,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Training of Spiking Neural Networks with Expectation-Propagation
An Expectation-Propagation framework trains spiking neural networks with mini-batches, supporting discrete or continuous weights and deterministic or stochastic spiking, and returns approximate posterior uncertainties.