How does a user's prior experience with deep learning impact accuracy? We present an initial study based on 31 participants with different levels of experience. Their task is to perform hyperparameter optimization for a given deep learning architecture. The results show a strong positive correlation between the participant's experience and the final performance. They additionally indicate that an experienced participant finds better solutions using fewer resources on average. The data suggests furthermore that participants with no prior experience follow random strategies in their pursuit of optimal hyperparameters. Our study investigates the subjective human factor in comparisons of state of the art results and scientific reproducibility in deep learning.
@article{arxiv.2008.05981,
title = {Black Magic in Deep Learning: How Human Skill Impacts Network Training},
author = {Kanav Anand and Ziqi Wang and Marco Loog and Jan van Gemert},
journal= {arXiv preprint arXiv:2008.05981},
year = {2020}
}
Comments
presented at the British Machine Vision Conference, 2020