功能兼容性作为持续神经学习的决定因素
Functional compatibility as a determinant of persistent neural learning
- Dublin City University（都柏林城市大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
该研究提出功能兼容性是持续神经学习的因果决定因素，通过受控实验验证其可推广至多类模型与任务，为解决神经网络稳定性-可塑性问题提供了新方向。
AI中文摘要：
人工神经网络能够获取新能力，但在持续学习时往往会损害现有能力。这种稳定性-可塑性问题催生了重放、正则化和约束更新方法，但目前仍不清楚输入学习本身的某个属性是否能决定在不破坏受保护行为的情况下可保留的内容。本文表明，功能兼容性（即新学习与必须保留的行为共存的程度）是持续学习的因果决定因素。据我们所知，这是首个受控因果论证，其中兼容性通过匹配的神经状态被刻意改变，且在共同的保留要求下对持续学习进行了测量。该效应可推广至独立学习方向、卷积和Transformer架构、视觉与文本任务以及不同随机种子。学习规则在利用可用兼容性的效率上存在差异，而保留约束限制了可存储的内容量。在更大的有限更新下，非线性几何改变了可用的学习机会，最终使匹配的兼容性连续体无法实现。这些结果确立了功能兼容性是可实验控制的持续神经学习原则，将问题从防止遗忘转向识别新学习的哪些组件可安全永久保留。
英文摘要：
Neural networks can acquire new capabilities while damaging existing ones, but what determines whether new learning persists remains unclear. We identify functional compatibility, the extent to which incoming learning can coexist with behaviour that must be preserved, as an experimentally manipulable causal determinant of persistence. From identical neural states, we vary compatibility while matching unrestricted learning opportunity and imposing a common retention requirement. Persistent learning increases with compatibility across independent directions, convolutional and transformer architectures, vision and text, and a ten-seed replication. Learning rules and retention constraints determine how much compatible opportunity is retained, whereas nonlinear geometry limits the matched intervention at larger update norms. Functional compatibility therefore reframes stability-plasticity from preventing forgetting to determining which new learning can coexist with existing function and persist.
