Topological Data Analysis of Decision Boundaries with Application to Model Selection
Pages: 5351 - 5360
Published: May 24, 2019
Abstract
We propose the labeled Cech 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...
Paper Details
Title
Topological Data Analysis of Decision Boundaries with Application to Model Selection
Published Date
May 24, 2019
Pages
5351 - 5360
Citation AnalysisPro
You’ll need to upgrade your plan to Pro
Looking to understand the true influence of a researcher’s work across journals & affiliations?
- Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
- Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.
Notes
History