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

12/16/2020
by   Sebastian Mežnar, et al.
0

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 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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

12/22/2020

Fractal Dimension Generalization Measure

Developing a robust generalization measure for the performance of machin...
12/14/2020

NeurIPS 2020 Competition: Predicting Generalization in Deep Learning

Understanding generalization in deep learning is arguably one of the mos...
01/16/2021

Robustness to Augmentations as a Generalization metric

Generalization is the ability of a model to predict on unseen domains an...
06/09/2021

Predicting Deep Neural Network Generalization with Perturbation Response Curves

The field of Deep Learning is rich with empirical evidence of human-like...
05/27/2020

Automatic salt deposits segmentation: A deep learning approach

One of the most important applications of seismic reflection is the hydr...
11/25/2020

Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs

Measuring the generalization performance of a Deep Neural Network (DNN) ...
06/03/2013

Predicting Parameters in Deep Learning

We demonstrate that there is significant redundancy in the parameterizat...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.