Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning
This addresses the need for low-power, personalized adaptation in edge applications like mobile healthcare, offering a novel solution for on-device learning.
The paper tackles the challenge of enabling Spiking Neural Networks (SNNs) to adapt quickly to new tasks on edge devices with minimal data, proposing an online-within-online meta-learning rule (OWOML-SNN) that supports lifelong learning without backpropagation.
Spiking Neural Networks (SNNs) have recently gained popularity as machine learning models for on-device edge intelligence for applications such as mobile healthcare management and natural language processing due to their low power profile. In such highly personalized use cases, it is important for the model to be able to adapt to the unique features of an individual with only a minimal amount of training data. Meta-learning has been proposed as a way to train models that are geared towards quick adaptation to new tasks. The few existing meta-learning solutions for SNNs operate offline and require some form of backpropagation that is incompatible with the current neuromorphic edge-devices. In this paper, we propose an online-within-online meta-learning rule for SNNs termed OWOML-SNN, that enables lifelong learning on a stream of tasks, and relies on local, backprop-free, nested updates.