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.

21 pages, 9 figures

References in corpus (1)

• Is a 4-bit synaptic weight resolution enough? - Constraints on enabling spike-timing dependent plasticity in neuromorphic hardware

Cited by in corpus (43)

• Memory and information processing in neuromorphic systems
• Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing
• Neuromorphic electronic circuits for building autonomous cognitive systems
• A silicon photonic modulator neuron
• Topological Principles of Control in Dynamical Network Systems
• An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture
• Unsupervised Heart-rate Estimation in Wearables With Liquid States and A Probabilistic Readout
• Characterization and Compensation of Network-Level Anomalies in Mixed-Signal Neuromorphic Modeling Platforms
• A Mixed-Signal Structured AdEx Neuron for Accelerated Neuromorphic Cores
• Accelerated physical emulation of Bayesian inference in spiking neural networks
• Principles of Neuromorphic Photonics
• Optoelectronic Intelligence
• Deterministic networks for probabilistic computing
• Pattern representation and recognition with accelerated analog neuromorphic systems
• Extending BrainScaleS OS for BrainScaleS-2
• Integrated-photonic characterization of single-photon detectors for use in neuromorphic synapses
• A Modular Workflow for Performance Benchmarking of Neuronal Network Simulations
• Harnessing adaptive dynamics in neuro-memristive nanowire networks for transfer learning
• The effect of heterogeneity on decorrelation mechanisms in spiking neural networks: a neuromorphic-hardware study
• A neuromorphic hardware architecture using the Neural Engineering Framework for pattern recognition
• Criticality or Supersymmetry Breaking ?
• Precise spiking motifs in neurobiological and neuromorphic data
• Structured Convolution Matrices for Energy-efficient Deep learning
• Neuromorphic Learning towards Nano Second Precision
• Self-Adaptive Spike-Time-Dependent Plasticity of Metal-Oxide Memristors
• Low-Power Neuromorphic Hardware for Signal Processing Applications
• Hardware-Friendly Implementation of Physical Reservoir Computing with CMOS-based Time-domain Analog Spiking Neurons
• Analog control with two Artificial Axons
• Point Neurons with Conductance-Based Synapses in the Neural Engineering Framework
• Event-based update of synapses in voltage-based learning rules
• Sparse Spiking Gradient Descent
• Synthetic Biology meets Neuromorphic Computing: Towards a bio-inspired Olfactory Perception System
• Benchmarking Deep Spiking Neural Networks on Neuromorphic Hardware
• An FPGA-based Massively Parallel Neuromorphic Cortex Simulator
• Energy Saving Additive Neural Network
• Toward bio-inspired information processing with networks of nano-scale switching elements
• Robustness from structure: Inference with hierarchical spiking networks on analog neuromorphic hardware
• Telling neuronal apples from oranges: analytical performance modeling of neural tissue simulations
• Spiking neurons with short-term synaptic plasticity form superior generative networks
• Bridging the Band Gap: What Device Physicists Need to Know About Machine Learning
• A neuronal dynamics study on a neuromorphic chip
• Ultrafast neural sampling with spiking nanolasers
• Polychrony as Chinampas