神经网络在渐变世界中会失去可塑性吗？
Do Neural Networks Lose Plasticity in a Gradually Changing World?
AI总结：
研究任务转换的突然性对神经网络可塑性损失的影响，通过输入/输出插值和任务采样模拟渐变环境，理论和实验表明可塑性损失严重程度与任务转换突然性密切相关，渐变环境下可显著减轻。
摘要：
持续学习已成为机器学习的热门话题。最近的研究发现了一个有趣的现象，称为可塑性丧失，指的是神经网络逐渐失去学习新任务的能力。然而，现有的可塑性研究很大程度上依赖于具有突然任务转换的基准测试，而没有检验突然性本身是否导致了观察到的可塑性损失。在本文中，我们通过输入/输出插值和任务采样模拟逐渐变化的环境，研究了转换突然性的作用。我们进行了理论和实证分析，表明可塑性损失的严重程度与任务转换的突然性密切相关，并且在环境逐渐变化时可以显著降低。
英文摘要：
Continual learning has become a trending topic in machine learning. Recent studies have discovered an interesting phenomenon called loss of plasticity, referring to neural networks gradually losing the ability to learn new tasks. However, existing plasticity research largely relies on benchmarks with abrupt task transitions, without examining whether the abruptness itself contributes to the observed plasticity loss. In this paper, we investigate the role of transition abruptness by simulating gradually changing environments through input/output interpolation and task sampling. We perform theoretical and empirical analysis, showing that the severity of plasticity loss is closely tied to the abruptness of task transitions, and can be substantially reduced when the environment changes gradually.
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。
