# Pattern representation and recognition with accelerated analog neuromorphic systems

## TL;DR

This paper explores methods to map biologically inspired spiking neural networks onto fast, low-power analog neuromorphic hardware, addressing challenges of analog variability through stabilization, robust architectures, and specialized training.

## Contribution

It introduces three strategies—auxiliary components, robust architectures, and a new training method—to improve the emulation of biologically realistic networks on analog neuromorphic systems.

## Key findings

- Experimental validation on neuromorphic hardware demonstrates improved stability.
- Robust architectures show resilience to analog component variability.
- Training method enables effective network emulation without precise system knowledge.

## Abstract

Despite being originally inspired by the central nervous system, artificial neural networks have diverged from their biological archetypes as they have been remodeled to fit particular tasks. In this paper, we review several possibilites to reverse map these architectures to biologically more realistic spiking networks with the aim of emulating them on fast, low-power neuromorphic hardware. Since many of these devices employ analog components, which cannot be perfectly controlled, finding ways to compensate for the resulting effects represents a key challenge. Here, we discuss three different strategies to address this problem: the addition of auxiliary network components for stabilizing activity, the utilization of inherently robust architectures and a training method for hardware-emulated networks that functions without perfect knowledge of the system's dynamics and parameters. For all three scenarios, we corroborate our theoretical considerations with experimental results on accelerated analog neuromorphic platforms.