Pattern representation and recognition with accelerated analog neuromorphic systems

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.

arXiv commentaccepted at ISCAS 2017

References in corpus (4)

• Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
• Six networks on a universal neuromorphic computing substrate
• Neuromorphic Hardware In The Loop: Training a Deep Spiking Network on the BrainScaleS Wafer-Scale System
• Stochastic inference with spiking neurons in the high-conductance state

Cited by in corpus (7)

• SpiNNaker 2: A 10 Million Core Processor System for Brain Simulation and Machine Learning
• Versatile emulation of spiking neural networks on an accelerated neuromorphic substrate
• Accelerated physical emulation of Bayesian inference in spiking neural networks
• Efficient Reward-Based Structural Plasticity on a SpiNNaker 2 Prototype
• Stochasticity from function -- why the Bayesian brain may need no noise
• Spiking neuromorphic chip learns entangled quantum states
• Spiking neurons with short-term synaptic plasticity form superior generative networks