A constructive method builds 2D deep ReLU CNNs that achieve near-optimal approximation rates for Korobov functions.
Statistical theory f or image classification using deep convo- lutional neural networks with cross-entropy loss
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Two-Dimensional Deep ReLU CNN Approximation for Korobov Functions: A Constructive Approach
A constructive method builds 2D deep ReLU CNNs that achieve near-optimal approximation rates for Korobov functions.