Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
SpikeLite: Lightweight Spiking Neural Networks for Time-Series Forecasting
Bang Hu, Changze Lv, Mingjie Li +3
Spiking neural networks (SNNs) offer an energy-efficient paradigm for time-series forecasting through spike-driven computation. However, recent SNN forecasters often pursue higher…
cs.LG2025
SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network
Huijing Zhang, Muyang Cao, Linshan Jiang +4
Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments. However, the scenario becomes p…