Inferring Convolutional Neural Networks' accuracies from their architectural characterizations

1 code implementation • 7 Jan 2020 • Duc Hoang, Jesse Hamer, Gabriel N. Perdue, Steven R. Young, Jonathan Miller, Anushree Ghosh

We characterize CNN's architecture by different attributes, and demonstrate that the attributes can be predictive of the networks' performance in two specific computer vision-based physics problems -- event vertex finding and hadron multiplicity classification in the MINERvA experiment at Fermi National Accelerator Laboratory.

Model Selection