Federated Neuromorphic Learning of Spiking Neural Networks for Low-Power Edge Intelligence
This work addresses low-power edge intelligence for devices with constrained data, offering an incremental improvement by combining federated learning with SNNs.
The paper tackles the problem of limited data for on-device training of Spiking Neural Networks (SNNs) by proposing Federated Learning-based SNN (FL-SNN), which uses local and global feedback to enable cooperative training across devices, achieving a flexible trade-off between communication load and accuracy.
Spiking Neural Networks (SNNs) offer a promising alternative to conventional Artificial Neural Networks (ANNs) for the implementation of on-device low-power online learning and inference. On-device training is, however, constrained by the limited amount of data available at each device. In this paper, we propose to mitigate this problem via cooperative training through Federated Learning (FL). To this end, we introduce an online FL-based learning rule for networked on-device SNNs, which we refer to as FL-SNN. FL-SNN leverages local feedback signals within each SNN, in lieu of backpropagation, and global feedback through communication via a base station. The scheme demonstrates significant advantages over separate training and features a flexible trade-off between communication load and accuracy via the selective exchange of synaptic weights.