KAC：用于持续学习的Kolmogorov-Arnold分类器
KAC: Kolmogorov-Arnold Classifier for Continual Learning
AI总结：
本文提出基于Kolmogorov-Arnold网络的KAC分类器，替换线性分类器用于持续学习，引入RBF函数提升稳定性，在多个基准上验证了性能提升。
摘要：
持续学习要求模型在连续的任务中不断训练而不遗忘。现有的大多数方法使用线性分类器，这些分类器在学习新任务时难以维持稳定的分类空间。受Kolmogorov-Arnold网络（KAN）在简单持续回归任务中保持学习稳定性的成功启发，我们开始探索其在更复杂的持续学习场景中的潜力。在本文中，我们介绍了Kolmogorov-Arnold分类器（KAC），一种基于KAN结构为持续学习开发的新型分类器。我们深入研究了KAN样条函数的影响，并引入径向基函数（RBF）以提高与持续学习的兼容性。我们在几种近期方法中用KAC替换线性分类器，并在各种持续学习基准上进行实验，所有实验均显示出性能提升，突显了KAC在持续学习中的有效性和鲁棒性。代码可在https://github.com/Ethanhuhuhu/KAC获取。
英文摘要：
Continual learning requires models to train continuously across consecutive tasks without forgetting. Most existing methods utilize linear classifiers, which struggle to maintain a stable classification space while learning new tasks. Inspired by the success of Kolmogorov-Arnold Networks (KAN) in preserving learning stability during simple continual regression tasks, we set out to explore their potential in more complex continual learning scenarios. In this paper, we introduce the Kolmogorov-Arnold Classifier (KAC), a novel classifier developed for continual learning based on the KAN structure. We delve into the impact of KAN's spline functions and introduce Radial Basis Functions (RBF) for improved compatibility with continual learning. We replace linear classifiers with KAC in several recent approaches and conduct experiments across various continual learning benchmarks, all of which demonstrate performance improvements, highlighting the effectiveness and robustness of KAC in continual learning. The code is available at https://github.com/Ethanhuhuhu/KAC.
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。
