Methods for applying the Neural Engineering Framework to neuromorphic hardware

TL;DR

This paper reviews software tools and theoretical methods for implementing the Neural Engineering Framework on neuromorphic hardware, enabling complex dynamical systems with realistic synaptic dynamics and delays.

Contribution

It introduces updated methods for applying the Neural Engineering Framework to neuromorphic hardware, accounting for nonideal synapses and transmission delays.

Findings

Methods enable implementation of linear and nonlinear systems

Account for heterogeneous synaptic time-constants

Applicable to various neuromorphic architectures

Abstract

We review our current software tools and theoretical methods for applying the Neural Engineering Framework to state-of-the-art neuromorphic hardware. These methods can be used to implement linear and nonlinear dynamical systems that exploit axonal transmission time-delays, and to fully account for nonideal mixed-analog-digital synapses that exhibit higher-order dynamics with heterogeneous time-constants. This summarizes earlier versions of these methods that have been discussed in a more biological context (Voelker & Eliasmith, 2017) or regarding a specific neuromorphic architecture (Voelker et al., 2017).