Six Networks on a Universal Neuromorphic Computing Substrate

Abstract

In this study, we present a highly configurable neuromorphic computing substrate and use it for emulating several types of neural networks. At the heart of this system lies a mixed-signal chip, with analog implementations of neurons and synapses and digital transmission of action potentials. Major advantages of this emulation device, which has been explicitly designed as a universal neural network emulator, are its inherent parallelism and high acceleration factor compared to conventional computers. Its configurability allows the realization of almost arbitrary network topologies and the use of widely varied neuronal and synaptic parameters. Fixed-pattern noise inherent to analog circuitry is reduced by calibration routines. An integrated development environment allows neuroscientists to operate the device without any prior knowledge of neuromorphic circuit design. As a showcase for the capabilities of the system, we describe the successful emulation of six different neural networks which cover a broad spectrum of both structure and functionality.

Predicting voluntary movements from motor cortical activity with neuromorphic hardware

“…Our results provide a proof of principle for the potential use of neuromorphic computing in a future biomedical application. [28]. The Spikey chip hosts analog neuron models (leaky integrate-and-fire with conductance-based synapses).…”

“…The neuromorphic chip hosts analog neuron models (leaky integrate-and-fire with conductance-based synapses). A detailed account of the operation of Spikey (including several examples) is provided in [28]. Therefore, we only provide an overview on a typical workflow for running a neuromorphic network on Spikey.…”

“…We used the Spikey neuromorphic system that has been developed at the Kirchhoff-Institute for Physics at Heidelberg University (Germany) [28]. Spikey contains a mixed-signal neuromorphic chip with analog neuron circuits and digital routing for spike events.…”

“…These weights are unit-less because they correspond to software-defined parameters with an arbitrary reference [28]. Connection weights per population are detailed in Table 1.…”

“…SpiNNaker [24], NeuroGrid [25], ROLLS [26], IBM's TrueNorth [27], or the systems developed at the University of Heidelberg [28], [29] (see [30] for a review). Aside from testing principles of neural computation [28], [31], [32], initial applications of neuromorphic hardware have been demonstrated for generic pattern recognition [27], [33]. These applications highlight the potential of this new technology to solve various widely investigated computing problems.…”