Topological structure of complex predictions

Tamal K. Dey, David F. Gleich, Meng Liu

Publication date: 28 July 2022

Abstract: Complex prediction models such as deep learning are the output from fitting machine learning, neural networks, or AI models to a set of training data. These are now standard tools in science. A key challenge with the current generation of models is that they are highly parameterized, which makes describing and interpreting the prediction strategies difficult. We use topological data analysis to transform these complex prediction models into pictures representing a topological view. The result is a map of the predictions that enables inspection. The methods scale up to large datasets across different domains and enable us to detect labeling errors in training data, understand generalization in image classification, and inspect predictions of likely pathogenic mutations in the BRCA1 gene.

Has companion code repository: https://github.com/mengliupurdue/graph-topological-data-analysis

This page was built for publication: Topological structure of complex predictions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6406403)