Continuous signal sparse encoding using analog neuromorphic variability

TL;DR

This paper introduces a biologically inspired, low-complexity encoding framework leveraging intrinsic neuronal variability for robust, fast, and continuous signal encoding on neuromorphic hardware, suitable for low-power temporal data processing.

Contribution

It presents a novel encoding scheme that uses intrinsic variability and minimal spikes, enabling robust, continuous, and linearly decodable signal representation on neuromorphic systems.

Findings

High robustness to noise and spike jitter

Effective linear decoding of stimulus parameters

Spontaneous emergence of stereotyped spiking patterns

Abstract

Achieving fast and reliable temporal signal encoding is crucial for low-power, always-on systems. While current spike-based encoding algorithms rely on complex networks or precise timing references, simple and robust encoding models can be obtained by leveraging the intrinsic properties of analog hardware substrates. We propose an encoding framework inspired by biological principles that leverages intrinsic neuronal variability to robustly encode continuous stimuli into spatio-temporal patterns, using at most one spike per neuron. The encoder has low model complexity, relying on a shallow network of heterogeneous neurons. It relies on an internal time reference, allowing for continuous processing. Moreover, stimulus parameters can be linearly decoded from the spiking patterns, granting fast information retrieval. Our approach, validated on both analog neuromorphic hardware and simulation, demonstrates high robustness to noise, spike jitter, and reduced heterogeneity. Consistently with biological observations, we observed the spontaneous emergence of patterns with stereotyped spiking order. The proposed encoding scheme facilitates fast, robust and continuous information processing, making it well-suited for low-power, low-latency processing of temporal data on analog neuromorphic substrates.