# Black Magic in Deep Learning: How Human Skill Impacts Network Training

arXiv: https://arxiv.org/abs/2008.05981 · HTML: https://mlsanity.com/paper/2008.05981/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Aug 2020.

## Built on by (most cited first, 4 of 4)

- [πBO: Augmenting Acquisition Functions with User Beliefs for Bayesian Optimization](https://mlsanity.com/paper/2204.11051/) (2022)
- [Explainable Artificial Intelligence: Precepts, Methods, and Opportunities for Research in Construction](https://mlsanity.com/paper/2211.06579/) (2022)
- [Explainable Artificial Intelligence in Construction: The Content, Context, Process, Outcome Evaluation Framework](https://mlsanity.com/paper/2211.06561/) (2022)
- [On Hyperparameter Tuning on the Test Set](https://mlsanity.com/paper/2610.05902/) (2026)

## Abstract (arXiv)

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.