路径协调的持续学习与神经正切核证明的可塑性：具有接近最先进性能的理论框架
Path-Coordinated Continual Learning with Neural Tangent Kernel-Justified Plasticity: A Theoretical Framework with Near State-of-the-Art Performance
AI总结：
本文提出一种结合NTK理论、Wilson置信区间和多指标路径评估的持续学习路径协调框架，在Split-CIFAR10上取得接近最先进性能，并揭示了NTK条件数阈值与学习容量极限的关系。
摘要：
灾难性遗忘是持续学习的基本问题之一，因为神经网络在训练新任务时会忘记之前学过的任务。所提出的框架是一个新的持续学习路径协调框架，它结合了具有原则性可塑性界限的Neural Tangent Kernel（NTK）理论、基于Wilson置信区间的统计验证，以及使用多个指标对路径质量的评估。实验评估表明，在Split-CIFAR10上实现了66.7%的平均准确率，代价是23.4%的灾难性遗忘，相比基线有巨大改进，取得的竞争性能非常接近最先进结果。此外，研究发现NTK条件数是学习能力极限的预测指标，表明在条件数$>10^{11}$时存在一个临界阈值。有趣的是，所提出的策略随着任务序列的推进表现出降低遗忘的趋势（从27%降至18%），这是一种系统稳定化。该框架以严格的统计保证验证了80%的已发现路径，并在中间任务上保持90-97%的保留率。分析中确定了持续学习环境的核心容量极限，并提供了增强自适应正则化的可操作见解。
英文摘要：
Catastrophic forgetting is one of the fundamental issues of continual learning because neural networks forget the tasks learned previously when trained on new tasks. The proposed framework is a new path-coordinated framework of continual learning that unites the Neural Tangent Kernel (NTK) theory of principled plasticity bounds, statistical validation by Wilson confidence intervals, and evaluation of path quality by the use of multiple metrics. Experimental evaluation shows an average accuracy of 66.7% at the cost of 23.4% catastrophic forgetting on Split-CIFAR10, a huge improvement over the baseline and competitive performance achieved, which is very close to state-of-the-art results. Further, it is found out that NTK condition numbers are predictive indicators of learning capacity limits, showing the existence of a critical threshold at condition number $>10^{11}$. It is interesting to note that the proposed strategy shows a tendency of lowering forgetting as the sequence of tasks progresses (27% to 18%), which is a system stabilization. The framework validates 80% of discovered paths with a rigorous statistical guarantee and maintains 90-97% retention on intermediate tasks. The core capacity limits of the continual learning environment are determined in the analysis, and actionable insights to enhance the adaptive regularization are offered.
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。
