人工智能
计算机科学
特征(语言学)
机器学习
监督学习
模式识别(心理学)
特征选择
支持向量机
拓扑数据分析
特征学习
特征提取
人工神经网络
理论(学习稳定性)
序列(生物学)
一般化
边距(机器学习)
作者
Anonymous,Xiumei Wang,Xingping Zhou
出处
期刊:Physical review
[American Physical Society]
日期:2026-10-05
卷期号:114 (20): 204102-
摘要
Supervised machine learning can help learn topological invariants for topological systems. However, it faces severe limitations when applied to non-Hermitian topological phases. The nonlinear nature of the non-Bloch topological invariant causes a sudden change in non-Hermitian or high-dimensional situations, while supervised machine learning does not have the ability to grasp the rule at this moment. We have rigorously demonstrated the limitation of supervised machine learning and systematically delineated the valid scale range for effective model predictions through generalization error bounds. By integrating the hypothesis space and the underlying physical mechanisms, our work establishes a generalized theoretical framework for evaluating the feasibility of supervised machine learning in topological phase identification.
科研通智能强力驱动
Strongly Powered by AbleSci AI