The reviewed record of science sign in
Pith

arxiv: 2201.10777 · v1 · pith:ZRWWXR3J · submitted 2022-01-26 · cs.NE · cs.LG

Meta-learning Spiking Neural Networks with Surrogate Gradient Descent

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:ZRWWXR3Jrecord.jsonopen to challenge →

classification cs.NE cs.LG
keywords learningmeta-learninggradientmamlneuromorphicsnnsspikingsurrogate
0
0 comments X
read the original abstract

Adaptive "life-long" learning at the edge and during online task performance is an aspirational goal of AI research. Neuromorphic hardware implementing Spiking Neural Networks (SNNs) are particularly attractive in this regard, as their real-time, event-based, local computing paradigm makes them suitable for edge implementations and fast learning. However, the long and iterative learning that characterizes state-of-the-art SNN training is incompatible with the physical nature and real-time operation of neuromorphic hardware. Bi-level learning, such as meta-learning is increasingly used in deep learning to overcome these limitations. In this work, we demonstrate gradient-based meta-learning in SNNs using the surrogate gradient method that approximates the spiking threshold function for gradient estimations. Because surrogate gradients can be made twice differentiable, well-established, and effective second-order gradient meta-learning methods such as Model Agnostic Meta Learning (MAML) can be used. We show that SNNs meta-trained using MAML match or exceed the performance of conventional ANNs meta-trained with MAML on event-based meta-datasets. Furthermore, we demonstrate the specific advantages that accrue from meta-learning: fast learning without the requirement of high precision weights or gradients. Our results emphasize how meta-learning techniques can become instrumental for deploying neuromorphic learning technologies on real-world problems.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.