Trainable Wavelet Neural Network for Non-Stationary Signals
Machine Learning
2022-05-09 v1
Abstract
This work introduces a wavelet neural network to learn a filter-bank specialized to fit non-stationary signals and improve interpretability and performance for digital signal processing. The network uses a wavelet transform as the first layer of a neural network where the convolution is a parameterized function of the complex Morlet wavelet. Experimental results, on both simplified data and atmospheric gravity waves, show the network is quick to converge, generalizes well on noisy data, and outperforms standard network architectures.
Cite
@article{arxiv.2205.03355,
title = {Trainable Wavelet Neural Network for Non-Stationary Signals},
author = {Jason Stock and Chuck Anderson},
journal= {arXiv preprint arXiv:2205.03355},
year = {2022}
}
Comments
AI for Earth and Space Science Workshop at the International Conference on Learning Representations (ICLR), April, 2022