pith. sign in

arxiv: 2012.09117 · v1 · pith:JBCMGFA2new · submitted 2020-12-16 · 💻 cs.LG · stat.ML

Predicting Generalization in Deep Learning via Metric Learning -- PGDL Shared task

classification 💻 cs.LG stat.ML
keywords generalizationlearningdeepcompetitionmodelspgdlpredictingachieved
0
0 comments X
read the original abstract

The competition "Predicting Generalization in Deep Learning (PGDL)" aims to provide a platform for rigorous study of generalization of deep learning models and offer insight into the progress of understanding and explaining these models. This report presents the solution that was submitted by the user \emph{smeznar} which achieved the eight place in the competition. In the proposed approach, we create simple metrics and find their best combination with automatic testing on the provided dataset, exploring how combinations of various properties of the input neural network architectures can be used for the prediction of their generalization.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.