神经坍缩：关于建模原理与泛化性的综述
Neural Collapse: A Review on Modelling Principles and Generalization
AI总结：
本文综述了深度分类网络训练终末阶段的神经坍缩现象，梳理其建模原理，并探讨该状态对模型泛化与迁移学习的影响及未来研究方向。
摘要：
深度分类神经网络在训练误差达到零时进入训练的终末阶段（TPT），并倾向于表现出引人关注的神经坍缩（NC）性质。神经坍缩本质上表示一种状态：最终隐藏层输出的类内变异性极小，且各类均值构成单纯形等角紧框架。这使得最后一层的行为简化为最近类中心决策规则。尽管该状态形式简单，但达到该状态的动力学过程及其影响尚未被完全理解。本文回顾了有助于对神经坍缩进行建模的原理，随后讨论该状态对神经网络泛化能力和迁移学习能力的影响。最后，我们讨论未来研究的潜在途径和方向。
英文摘要：
Deep classifier neural networks enter the terminal phase of training (TPT) when training error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural collapse essentially represents a state at which the within-class variability of final hidden layer outputs is infinitesimally small and their class means form a simplex equiangular tight frame. This simplifies the last layer behaviour to that of a nearest-class center decision rule. Despite the simplicity of this state, the dynamics and implications of reaching it are yet to be fully understood. In this work, we review the principles which aid in modelling neural collapse, followed by the implications of this state on generalization and transfer learning capabilities of neural networks. Finally, we conclude by discussing potential avenues and directions for future research.
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。
