EqSpike: Spike-driven Equilibrium Propagation for Neuromorphic Implementations

10/15/2020
by   Erwann Martin, et al.
6

Neuromorphic systems achieve high energy efficiency by computing with spikes, in a brain-inspired way. However, finding spike-based learning algorithms that can be implemented within the local constraints of neuromorphic systems, while achieving high accuracy, remains a formidable challenge. Equilibrium Propagation is a hardware-friendly counterpart of backpropagation which only involves spatially local computations and applies to recurrent neural networks with static inputs. So far, hardware-oriented studies of Equilibrium Propagation focused on rate-based networks. In this work, we develop a spiking neural network algorithm called EqSpike, compatible with neuromorphic systems, which learns by Equilibrium Propagation. Through simulations, we obtain a test recognition accuracy of 96.9 Propagation, and comparing favourably to alternative learning techniques for spiking neural networks. We show that EqSpike implemented in silicon neuromorphic technology could reduce the energy consumption of inference and training by up to three orders of magnitude compared to GPUs. Finally, we also show that during learning, EqSpike weight updates exhibit a form of Spike Timing Dependent Plasticity, highlighting a possible connection with biology.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/24/2023

Spikingformer: Spike-driven Residual Learning for Transformer-based Spiking Neural Network

Spiking neural networks (SNNs) offer a promising energy-efficient altern...
research
07/26/2013

Memcapacitive neural networks

We show that memcapacitive (memory capacitive) systems can be used as sy...
research
09/08/2020

Nonlinear computations in spiking neural networks through multiplicative synapses

The brain performs many nonlinear computations through intricate spiking...
research
10/13/2022

Real Spike: Learning Real-valued Spikes for Spiking Neural Networks

Brain-inspired spiking neural networks (SNNs) have recently drawn more a...
research
11/16/2021

From Convolutions towards Spikes: The Environmental Metric that the Community currently Misses

Today, the AI community is obsessed with 'state-of-the-art' scores (80 p...
research
05/23/2023

Toward spike-based stochastic neural computing

Inspired by the highly irregular spiking activity of cortical neurons, s...
research
09/14/2022

Sequence Learning using Equilibrium Propagation

Equilibrium Propagation (EP) is a powerful and more bio-plausible altern...

Please sign up or login with your details

Forgot password? Click here to reset