ETLP: Event-based Three-factor Local Plasticity for online learning with neuromorphic hardware

Abstract

Neuromorphic perception with event-based sensors, asynchronous hardware and spiking neurons is showing promising results for real-time and energy-efficient inference in embedded systems. The next promise of brain-inspired computing is to enable adaptation to changes at the edge with online learning. However, the parallel and distributed architectures of neuromorphic hardware based on co-localized compute and memory imposes locality constraints to the on-chip learning rules. We propose in this work the Event-based Three-factor Local Plasticity (ETLP) rule that uses (1) the pre-synaptic spike trace, (2) the post-synaptic membrane voltage and (3) a third factor in the form of projected labels with no error calculation, that also serve as update triggers. We apply ETLP with feedforward and recurrent spiking neural networks on visual and auditory event-based pattern recognition, and compare it to Back-Propagation Through Time (BPTT) and eProp. We show a competitive performance in accuracy with a clear advantage in the computational complexity for ETLP. We also show that when using local plasticity, threshold adaptation in spiking neurons and a recurrent topology are necessary to learn spatio-temporal patterns with a rich temporal structure. Finally, we provide a proof of concept hardware implementation of ETLP on FPGA to highlight the simplicity of its computational primitives and how they can be mapped into neuromorphic hardware for online learning with low-energy consumption and real-time interaction.

References in corpus (15)

• Neuromorphic computing with multi-memristive synapses
• STDP-based spiking deep convolutional neural networks for object recognition
• Neuromorphic electronic circuits for building autonomous cognitive systems
• SuperSpike: Supervised learning in multi-layer spiking neural networks
• A 0.086-mm${}^2$ 12.7-pJ/SOP 64k-Synapse 256-Neuron Online-Learning Digital Spiking Neuromorphic Processor in 28nm CMOS
• The Computational Limits of Deep Learning
• Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules
• Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• Towards Biologically Plausible Deep Learning
• Neuromorphic Deep Learning Machines
• Direct Feedback Alignment Provides Learning in Deep Neural Networks
• ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescales
• Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks
• Understanding Synthetic Gradients and Decoupled Neural Interfaces

Cited by in corpus (2)

• A Realistic Simulation Framework for Analog/Digital Neuromorphic Architectures
• TESS: A Scalable Temporally and Spatially Local Learning Rule for Spiking Neural Networks