A new parameter reconstruction method achieves globally optimal training for spiking neural networks by convexifying parallel recurrent threshold networks that include SNNs as a special case.
The Convex Geometry of Backpropagation: Neural Network Gradient Flows Converge to Extreme Points of the Dual Convex Program, October 2021
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.NE 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Globally Optimal Training of Spiking Neural Networks via Parameter Reconstruction
A new parameter reconstruction method achieves globally optimal training for spiking neural networks by convexifying parallel recurrent threshold networks that include SNNs as a special case.