用类脑脉冲网络实现持续学习，避免遗忘。
Continual Learning with Columnar Spiking Neural Networks
- 基于微柱结构的脉冲神经网络，采用局部学习规则。
- 十次连续任务中保持92%准确率，首任务仅降4%。
- 适合研究生物可解释性学习与稳定持续学习者。
持续学习是生物神经系统的关键特征，但人工神经网络常出现灾难性遗忘。本文提出基于列状组织的脉冲神经网络（CoLaNET），采用生物合理的学习规则实现稳定的持续学习。实验表明，当新任务与旧任务无共享结构时，其微柱结构能最高效适应。通过调节超参数，可控制保留旧知识（稳定性）与获取新信息（可塑性）的平衡。在两个基准测试中评估：一是十次像素置换的排列MNIST任务，二是MNIST/EMNIST双任务设置。模型成功学习十次连续任务，各任务准确率维持在92%，在完成九个后续任务后，首任务性能仅下降4%。
原文摘要 · Abstract (English)
Continual learning is a key feature of biological neural systems, but artificial neural networks often suffer from catastrophic forgetting. Instead of backpropagation, biologically plausible learning algorithms may enable stable continual learning. This study proposes columnar-organized spiking neural networks (SNNs) with local learning rules for continual learning and catastrophic forgetting. Using CoLaNET (Columnar Layered Network), we show that its microcolumns adapt most efficiently to new tasks when they lack shared structure with prior learning. We demonstrate how CoLaNET hyperparameters govern the trade-off between retaining old knowledge (stability) and acquiring new information (plasticity). We evaluate CoLaNET on two benchmarks: Permuted MNIST (ten sequential pixel-permuted tasks) and a two-task MNIST/EMNIST setup. Our model learns ten sequential tasks effectively, maintaining 92% accuracy on each. It shows low forgetting, with only 4% performance degradation on the first task after training on nine subsequent tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。