Harnessing Slow Dynamics in Neuromorphic Computation

TL;DR

This paper explores methods to slow down the fast dynamics of analog neuromorphic systems, demonstrating that harnessing slow dynamics can improve real-time signal processing performance.

Contribution

It proposes solutions to slow down on-chip spiking neural networks and empirically shows performance improvements in real-time tasks.

Findings

Slow dynamics can be effectively harnessed in neuromorphic systems.

Performance boosts observed in real-time signal processing tasks.

Analog neuromorphic systems benefit from timescale matching.

Abstract

Neuromorphic Computing is a nascent research field in which models and devices are designed to process information by emulating biological neural systems. Thanks to their superior energy efficiency, analog neuromorphic systems are highly promising for embedded, wearable, and implantable systems. However, optimizing neural networks deployed on these systems is challenging. One main challenge is the so-called timescale mismatch: Dynamics of analog circuits tend to be too fast to process real-time sensory inputs. In this thesis, we propose a few working solutions to slow down dynamics of on-chip spiking neural networks. We empirically show that, by harnessing slow dynamics, spiking neural networks on analog neuromorphic systems can gain non-trivial performance boosts on a battery of real-time signal processing tasks.