# Trainable Wavelet Neural Network for Non-Stationary Signals

arXiv: https://arxiv.org/abs/2205.03355 · HTML: https://mlsanity.com/paper/2205.03355/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 6 references that are in the map.
- First posted on arXiv 6 May 2022.

## Builds on (most cited first, 2 of 2)

- [Speaker Recognition from Raw Waveform with SincNet](https://mlsanity.com/paper/1808.00158/) (2018)
- [Deep Adaptive Wavelet Network](https://mlsanity.com/paper/1912.05035/) (2019)

## Built on by (most cited first, 2 of 2)

- [Tools for Extracting Spatio-Temporal Patterns in Meteorological Image Sequences: From Feature Engineering to Attention-Based Neural Networks](https://mlsanity.com/paper/2210.12310/) (2022)
- [Wavelet Predictive Representations for Non-Stationary Reinforcement Learning](https://mlsanity.com/paper/2510.04507/) (2025)

## Abstract (arXiv)

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.