A Mixed-Signal Structured AdEx Neuron for Accelerated Neuromorphic Cores

Abstract

Here we describe a multi-compartment neuron circuit based on the Adaptive-Exponential I&F (AdEx) model, developed for the second-generation BrainScaleS hardware. Based on an existing modular Leaky Integrate-and-Fire (LIF) architecture designed in 65 nm CMOS, the circuit features exponential spike generation, neuronal adaptation, inter-compartmental connections as well as a conductance-based reset. The design reproduces a diverse set of firing patterns observed in cortical pyramidal neurons. Further, it enables the emulation of sodium and calcium spikes, as well as N-Methyl-D-Aspartate (NMDA) plateau potentials known from apical and thin dendrites. We characterize the AdEx circuit extensions and exemplify how the interplay between passive and non-linear active signal processing enhances the computational capabilities of single (but structured) on-chip neurons.

arXiv comment11 pages, 17 figures (including author photographs)

References in corpus (3)

• Six networks on a universal neuromorphic computing substrate
• Neuromorphic Hardware In The Loop: Training a Deep Spiking Network on the BrainScaleS Wafer-Scale System
• An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture

Cited by in corpus (10)

• An Accelerated LIF Neuronal Network Array for a Large Scale Mixed-Signal Neuromorphic Architecture
• Bottom-up and top-down approaches for the design of neuromorphic processing systems: Tradeoffs and synergies between natural and artificial intelligence
• Versatile emulation of spiking neural networks on an accelerated neuromorphic substrate
• CMOS-based area-and-power-efficient neuron and synapse circuits for time-domain analog spiking neural networks
• An ultra-low-power sigma-delta neuron circuit
• Fast and energy-efficient neuromorphic deep learning with first-spike times
• Scalable Superconductor Neuron with Ternary Synaptic Connections for Ultra-Fast SNN Hardware
• Backpropagation through space, time, and the brain
• Closed-loop experiments on the BrainScaleS-2 architecture
• Simulation-based Inference for Model Parameterization on Analog Neuromorphic Hardware