lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents. (arXiv:2205.12295v1 [cs.NE])

Recent advances have shown that SNN-based systems can efficiently perform
unsupervised continual learning due to their bio-plausible learning rule, e.g.,
Spike-Timing-Dependent Plasticity (STDP). Such learning capabilities are
especially beneficial for use cases like autonomous agents (e.g., robots and
UAVs) that need to continuously adapt to dynamically changing
scenarios/environments, where new data gathered directly from the environment
may have novel features that should be learned online. Current state-of-the-art
works employ high-precision weights (i.e., 32 bit) for both training and
inference phases, …

agents arxiv autonomous continual enabling learning network neural network precision processing spiking neural network unsupervised