Topological Structure is Predictive of Deep Neural Network Success in Learning
Topological Structure is Predictive of Deep Neural Network Success in Learning
Christopher Griffin,Trevor K. Karn,Benjamin Apple
2023 · DOI: 10.48550/arXiv.2301.09734
arXiv.org · 2 Citations
TLDR
It is shown that fully interpretable topological classifiers are able to perform nearly as well as their DNN counterparts, and the simplicity in their topological structure explains the majority of the DNN’s ability to operate on these data sets.