Fast and energy-efficient neuromorphic deep learning with first-spike times

Abstract

For a biological agent operating under environmental pressure, energy consumption and reaction times are of critical importance. Similarly, engineered systems are optimized for short time-to-solution and low energy-to-solution characteristics. At the level of neuronal implementation, this implies achieving the desired results with as few and as early spikes as possible. With time-to-first-spike coding both of these goals are inherently emerging features of learning. Here, we describe a rigorous derivation of a learning rule for such first-spike times in networks of leaky integrate-and-fire neurons, relying solely on input and output spike times, and show how this mechanism can implement error backpropagation in hierarchical spiking networks. Furthermore, we emulate our framework on the BrainScaleS-2 neuromorphic system and demonstrate its capability of harnessing the system's speed and energy characteristics. Finally, we examine how our approach generalizes to other neuromorphic platforms by studying how its performance is affected by typical distortive effects induced by neuromorphic substrates.

arXiv comment24 pages, 11 figures

References in corpus (27)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Language Models are Few-Shot Learners
• Deep Learning in Spiking Neural Networks
• STDP-based spiking deep convolutional neural networks for object recognition
• A scalable multi-core architecture with heterogeneous memory structures for Dynamic Neuromorphic Asynchronous Processors (DYNAPs)
• SuperSpike: Supervised learning in multi-layer spiking neural networks
• Event-Driven Contrastive Divergence for Spiking Neuromorphic Systems
• S4NN: temporal backpropagation for spiking neural networks with one spike per neuron
• Supervised Learning in Multilayer Spiking Neural Networks
• Surrogate Gradient Learning in Spiking Neural Networks
• Demonstrating Advantages of Neuromorphic Computation: A Pilot Study
• Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines
• 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
• Biologically plausible deep learning -- but how far can we go with shallow networks?
• Training Spiking Deep Networks for Neuromorphic Hardware
• Stochastic inference with spiking neurons in the high-conductance state
• Characterization and Compensation of Network-Level Anomalies in Mixed-Signal Neuromorphic Modeling Platforms
• A Mixed-Signal Structured AdEx Neuron for Accelerated Neuromorphic Cores
• Versatile emulation of spiking neural networks on an accelerated neuromorphic substrate
• Accelerated physical emulation of Bayesian inference in spiking neural networks
• Stochasticity from function -- why the Bayesian brain may need no noise
• Stochastic inference with deterministic spiking neurons
• Deterministic networks for probabilistic computing
• Extending BrainScaleS OS for BrainScaleS-2
• Deep Spiking Neural Network with Spike Count based Learning Rule
• Fast and energy-efficient neuromorphic deep learning with first-spike times

Cited by in corpus (1)

• Fast and energy-efficient neuromorphic deep learning with first-spike times