In-Hardware Learning of Multilayer Spiking Neural Networks on a Neuromorphic Processor

TL;DR

This paper introduces a biologically plausible spike-based backpropagation algorithm adapted for neuromorphic hardware, enabling low-power, online supervised learning of multilayer spiking neural networks on the Intel Loihi chip for mobile applications.

Contribution

It presents a novel spike-based backpropagation algorithm suitable for neuromorphic hardware, facilitating in-hardware online learning of multilayer SNNs.

Findings

Successful implementation on Intel Loihi chip

Achieved promising accuracy on multiple datasets

Demonstrated energy-efficient incremental learning

Abstract

Although widely used in machine learning, backpropagation cannot directly be applied to SNN training and is not feasible on a neuromorphic processor that emulates biological neuron and synapses. This work presents a spike-based backpropagation algorithm with biological plausible local update rules and adapts it to fit the constraint in a neuromorphic hardware. The algorithm is implemented on Intel Loihi chip enabling low power in-hardware supervised online learning of multilayered SNNs for mobile applications. We test this implementation on MNIST, Fashion-MNIST, CIFAR-10 and MSTAR datasets with promising performance and energy-efficiency, and demonstrate a possibility of incremental online learning with the implementation.