Pattern representation and recognition with accelerated analog neuromorphic systems
This work addresses hardware implementation issues for neuromorphic computing, but it is incremental as it reviews and applies existing strategies.
The paper tackles the challenge of mapping artificial neural networks to biologically realistic spiking networks for emulation on fast, low-power neuromorphic hardware, particularly addressing analog component imperfections, and presents three strategies with experimental validation on accelerated platforms.
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.