Fast on-device adaptation for spiking neural networks via online-within-online meta-learning
Document Type
Conference Proceeding
Publication Date
6-5-2021
Abstract
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.
Identifier
85115418988 (Scopus)
ISBN
[9781665428255]
Publication Title
2021 IEEE Data Science and Learning Workshop Dslw 2021
External Full Text Location
https://doi.org/10.1109/DSLW51110.2021.9523405
Grant
1525629
Fund Ref
National Science Foundation
Recommended Citation
Rosenfeld, Bleema; Rajendran, Bipin; and Simeone, Osvaldo, "Fast on-device adaptation for spiking neural networks via online-within-online meta-learning" (2021). Faculty Publications. 4049.
https://digitalcommons.njit.edu/fac_pubs/4049