学习动力学的定律与学习者的核心
Laws of Learning Dynamics and the Core of Learners
AI总结：
本文提出了一种基于熵的终身集成学习方法，通过构建免疫机制有效防御对抗攻击，提升了在强扰动下的模型准确性。
摘要：
我们制定了支配学习动力学的基本定律，即守恒定律和总熵的减少。在此框架内，我们引入了一种基于熵的终身集成学习方法。我们通过构建免疫机制来防御针对CIFAR-10数据集的基于迁移的对抗攻击，以评估其有效性。与通过简单平均清洁样本和对抗样本专门化模型形成的朴素集成相比，所得到的logifold在大多数测试用例中具有更高的准确性，特别是在强扰动下有特别显著的提升。
英文摘要：
We formulate the fundamental laws governing learning dynamics, namely the conservation law and the decrease of total entropy. Within this framework, we introduce an entropy-based lifelong ensemble learning method. We evaluate its effectiveness by constructing an immunization mechanism to defend against transfer-based adversarial attacks on the CIFAR-10 dataset. Compared with a naive ensemble formed by simply averaging models specialized on clean and adversarial samples, the resulting logifold achieves higher accuracy in most test cases, with particularly large gains under strong perturbations.
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。
