Frequency-adaptive tensor neural networks are proposed to overcome the frequency principle in TNNs for high-dimensional multi-scale problems by incorporating random Fourier features and 1D DFT on component functions.
Yu, et al., The deep Ritz method: A deep learning-based numerical algorithm for solving variational problems, Communications in Mathematics and Statistics 6 (1) (2018) 1–12
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Frequency-adaptive tensor neural networks for high-dimensional multi-scale problems
Frequency-adaptive tensor neural networks are proposed to overcome the frequency principle in TNNs for high-dimensional multi-scale problems by incorporating random Fourier features and 1D DFT on component functions.