Low-Bit Data Processing Using Multiple-Output Spiking Neurons with Non-linear Reset Feedback

TL;DR

This paper introduces a novel multiple-output spiking neuron model with a non-linear reset feedback mechanism, enabling low-bit data processing and improved stability in neuromorphic computing applications.

Contribution

The paper proposes a new spiking neuron model combining linear state transitions with non-linear reset feedback, bridging SNNs and deep state-space models for enhanced temporal processing.

Findings

Achieves performance comparable to existing SNN benchmarks.

Overcomes instability issues with the reset mechanism.

Enables learning with unstable linear neuron dynamics.

Abstract

Neuromorphic computing is an emerging technology enabling low-latency and energy-efficient signal processing. A key algorithmic tool in neuromorphic computing is spiking neural networks (SNNs). SNNs are biologically inspired neural networks which utilize stateful neurons, and provide low-bit data processing by encoding and decoding information using spikes. Similar to SNNs, deep state-space models (SSMs) utilize stateful building blocks. However, deep SSMs, which recently achieved competitive performance in various temporal modeling tasks, are typically designed with high-precision activation functions and no reset mechanisms. To bridge the gains offered by SNNs and the recent deep SSM models, we propose a novel multiple-output spiking neuron model that combines a linear, general SSM state transition with a non-linear feedback mechanism through reset. Compared to the existing neuron models for SNNs, our proposed model clearly conceptualizes the differences between the spiking function, the reset condition and the reset action. The experimental results on various tasks, i.e., a keyword spotting task, an event-based vision task and a sequential pattern recognition task, show that our proposed model achieves performance comparable to existing benchmarks in the SNN literature. Our results illustrate how the proposed reset mechanism can overcome instability and enable learning even when the linear part of neuron dynamics is unstable, allowing us to go beyond the strictly enforced stability of linear dynamics in recent deep SSM models.