Edge spiking neural networks learn locally and in parallel during sensing
Learning While Inferring: Local and Parallel Learning for Edge SNNs across Sensing Modalities
Neural and Evolutionary Computing
Summary
Devices that process sensory data close to where it's collected need to learn and adapt continually without using too much power or memory. The authors explored a new way for spiking neural networks to update their learning while still making predictions, unlike standard methods that have to pause to learn. Their approach uses two separate networks working at the same time to teach each other locally, letting the device learn continuously and efficiently. This method performs almost as well as traditional ones, uses less energy during training, and can adapt to new tasks with less data.
What this means in practice
- •For embedded device engineers: Build energy-efficient edge sensors that adapt in real time without interrupting their inference process.
- •For mobile robot developers: Enable robots to continuously learn from multiple sensor types while operating under strict power and compute limits.
Authors
Yanxun Zhang, Yifei Wang, Changze Lv, Jingwen Xu, Yiyang Lu, Xiaohua Wang, Di Yu, Xin Du, Xiaoqing Zheng
Abstract
Edge intelligence requires models to sense continuously in real time and to keep adapting on-device, all under tight compute, energy, and memory budgets. Although spiking neural networks (SNNs) enable efficient event-driven inference, standard surrogate-gradient backpropagation (BP) serializes updates and blocks ongoing inference. We investigate Bidirectional Spike-Based Distillation (BSD) as an on-device learning principle that lets edge SNNs learn while inferring. BSD couples a stimulus-driven forward network with an independent target-driven reverse network and aligns their intermediate representations through local objectives. Because the two pathways have disjoint computation graphs until alignment, forward inference, reverse inference, and stage-wise updates can run concurrently. On 25 benchmarks spanning the five sensing modalities of SOUL, BSD stays within 3.8 percentage points of matched BP baselines on average, while only its forward branch is needed at deployment. The learned representations also transfer well to few-shot class-incremental learning without replaying past data. By removing the dense floating-point backward chain, BSD reduces the projected training latency to $0.72\times$ and the estimated training energy to $0.36\times$ that of BP.