基于柱状脉冲神经网络的持续学习
Continual Learning with Columnar Spiking Neural Networks
AI总结：
本文提出基于CoLaNET的柱状脉冲神经网络，利用局部学习规则实现持续学习，在Permuted MNIST和MNIST/EMNIST基准上有效缓解灾难性遗忘，仅4%性能下降。
摘要：
持续学习是生物神经系统的关键特征，但人工神经网络常常遭受灾难性遗忘。与反向传播不同，具有生物学合理性的学习算法可能实现稳定的持续学习。本研究提出了采用局部学习规则的柱状组织脉冲神经网络（SNN），用于持续学习和应对灾难性遗忘。利用CoLaNET（柱状分层网络），我们表明其微柱在与先前学习缺乏共享结构时，对新任务的适应效率最高。我们展示了CoLaNET的超参数如何调控保留旧知识（稳定性）与获取新信息（可塑性）之间的权衡。我们在两个基准上评估CoLaNET：Permuted MNIST（十个顺序像素置换任务）和一个双任务MNIST/EMNIST设置。我们的模型有效学习了十个顺序任务，在每个任务上保持92%的准确率。它表现出较低的遗忘，在后续九个任务上训练后，第一个任务的性能仅下降4%。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
