Shallow neural networks with time-frequency localized activations achieve dimension-independent Sobolev approximation rates of order N^{-1/2} for functions in weighted modulation spaces.
Modulation Spaces and the Curse of Dimensionality
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
A partially deterministic Bernoulli sampling scheme for unitary-matrix compressed sensing that improves sample complexity and adds denoising guarantees over fully random methods.
citing papers explorer
-
Time-Frequency Analysis for Neural Networks
Shallow neural networks with time-frequency localized activations achieve dimension-independent Sobolev approximation rates of order N^{-1/2} for functions in weighted modulation spaces.
-
Partially deterministic sampling for compressed sensing with denoising guarantees
A partially deterministic Bernoulli sampling scheme for unitary-matrix compressed sensing that improves sample complexity and adds denoising guarantees over fully random methods.