Topological Data Analysis of Decision Boundaries with Application to Model Selection

Autor:	Ramamurthy, Karthikeyan Natesan, Varshney, Kush R., Mody, Krishnan
Rok vydání:	2018
Předmět:	Statistics - Machine Learning Computer Science - Learning
Druh dokumentu:	Working Paper
Popis:	We propose the labeled \v{C}ech complex, the plain labeled Vietoris-Rips complex, and the locally scaled labeled Vietoris-Rips complex to perform persistent homology inference of decision boundaries in classification tasks. We provide theoretical conditions and analysis for recovering the homology of a decision boundary from samples. Our main objective is quantification of deep neural network complexity to enable matching of datasets to pre-trained models; we report results for experiments using MNIST, FashionMNIST, and CIFAR10. Comment: Reproducible software available, 17 pages, 10 figures, 12 tables
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1805.09949 Zobrazit plný text záznamu View this record from Arxiv