Why is topology hard to learn?
D. O. Oriekhov, Stan Bergkamp, Guliuxin Jin, Juan Daniel Torres Luna, Badr Zouggari, Sibren van der Meer, Naoual El Yazidi, and Eliska Greplova
人们对使用机器学习来近似物理概念的关注已经很多了。 然而,由于机器学习技术可解释性的挑战,物理机器学习模型能够学习的问题仍然是开放的。 在这里,我们将物理量的概念及其机器学习近似于神经网络在物理学中的原始应用:拓扑相分类。 我们构建了一个混合的张量-神经网络对象,它准确地表达了真实的空间拓扑不变性,并严格评估其训练性和概括性。 具体来说,我们将张量神经网络的准确性和可训练性与多种类型的神经网络进行了基准测试,从而证明了可训练性和代表性能力的差异。 我们的工作突出了学习拓扑不变性的挑战,并构成了在凝聚态物理中实现更准确、更可推广的机器学习表征的垫脚石。
Much attention has been devoted to the use of machine learning to approximate physical concepts. Yet, due to challenges in interpretability of machine learning techniques, the question of what physics machine learning models are able to learn remains open. Here we bridge the concept a physical quantity and its machine learning approximation in the context of the original application of neural networks in physics: topological phase classification. We construct a hybrid tensor-neural network objec...