Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networks
This work addresses the problem of efficient on-chip SNN training for neuromorphic computing, though it appears incremental as it builds on existing online training methods.
The authors tackled the challenge of training spiking neural networks (SNNs) in a biologically plausible and hardware-friendly way by proposing an online pseudo-zeroth-order (OPZO) method, which achieved similar performance to spatial backpropagation on neuromorphic and static datasets with estimated low training costs.
Brain-inspired neuromorphic computing with spiking neural networks (SNNs) is a promising energy-efficient computational approach. However, successfully training SNNs in a more biologically plausible and neuromorphic-hardware-friendly way is still challenging. Most recent methods leverage spatial and temporal backpropagation (BP), not adhering to neuromorphic properties. Despite the efforts of some online training methods, tackling spatial credit assignments by alternatives with comparable performance as spatial BP remains a significant problem. In this work, we propose a novel method, online pseudo-zeroth-order (OPZO) training. Our method only requires a single forward propagation with noise injection and direct top-down signals for spatial credit assignment, avoiding spatial BP's problem of symmetric weights and separate phases for layer-by-layer forward-backward propagation. OPZO solves the large variance problem of zeroth-order methods by the pseudo-zeroth-order formulation and momentum feedback connections, while having more guarantees than random feedback. Combining online training, OPZO can pave paths to on-chip SNN training. Experiments on neuromorphic and static datasets with fully connected and convolutional networks demonstrate the effectiveness of OPZO with similar performance compared with spatial BP, as well as estimated low training costs.