Spiking neural networks have Rademacher complexity bounds that scale exponentially with depth and spike sequence duration, superlinearly and subquadratically with width, polynomially with parameter norm, and inversely with training sample count, independent of internal neuron computations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.NE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Generalization Bounds of Spiking Neural Networks via Rademacher Complexity
Spiking neural networks have Rademacher complexity bounds that scale exponentially with depth and spike sequence duration, superlinearly and subquadratically with width, polynomially with parameter norm, and inversely with training sample count, independent of internal neuron computations.