Scale-covariant spiking wavelets

TL;DR

This paper introduces a novel approach linking wavelet transforms with spiking neural networks via scale-space theory, enabling energy-efficient signal processing with potential for improved neural computation.

Contribution

It presents a method to implement discrete wavelets in spiking neural networks using scale-covariance properties of leaky integrate-and-fire neurons, bridging wavelet theory and neural models.

Findings

Successful demonstration of wavelet approximation in spiking networks

Feasibility of reconstructing signals from spiking wavelet representations

Potential for more energy-efficient signal processing algorithms

Abstract

We establish a theoretical connection between wavelet transforms and spiking neural networks through scale-space theory. We rely on the scale-covariant guarantees in the leaky integrate-and-fire neurons to implement discrete mother wavelets that approximate continuous wavelets. A reconstruction experiment demonstrates the feasibility of the approach and warrants further analysis to mitigate current approximation errors. Our work suggests a novel spiking signal representation that could enable more energy-efficient signal processing algorithms.