The training of neural networks is usually monitored with a validation (holdout) set to estimate the generalization of the model. This is done instead of measuring intrinsic properties of the model to determine whether it is learning appropriately. In this work, we suggest studying the training of neural networks with Algebraic Topology, specifically Persistent Homology (PH). Using simplicial complex representations of neural networks, we study the PH diagram distance evolution on the neural network learning process with different architectures and several datasets. Results show that the PH diagram distance between consecutive neural network states correlates with the validation accuracy, implying that the generalization error of a neural network could be intrinsically estimated without any holdout set.
翻译:神经网络的培训通常通过验证( 停止) 来监测, 以估计模型的概括性。 这样做不是衡量模型的内在特性, 以确定模型的学习是否恰当。 在这项工作中, 我们建议研究对神经网络的培训, 使用代数地形学, 特别是持久性同理学( PH ) 。 使用神经网络的简单复杂的表达方式, 我们研究神经网络学习过程的 PH 图距离演变过程, 使用不同的结构和多个数据集 。 结果显示, 连续神经网络之间的 PH 图距离与校验准确性相关, 意味着神经网络的一般错误可以在不设任何屏蔽装置的情况下进行内在估计 。