# Hide-and-Seek: A Template for Explainable AI

arXiv: https://arxiv.org/abs/2005.00130 · HTML: https://mlsanity.com/paper/2005.00130/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2020.

## Built on by (most cited first, 3 of 3)

- [Improvement of a Prediction Model for Heart Failure Survival through Explainable Artificial Intelligence](https://mlsanity.com/paper/2108.10717/) (2021)
- [Development and evaluation of an Explainable Prediction Model for Chronic Kidney Disease Patients based on Ensemble Trees](https://mlsanity.com/paper/2105.10368/) (2021)
- [Hide&Seek: Learning to Explain in an End-to-End Differentiable Network](https://mlsanity.com/paper/2608.16689/) (2026)

## Abstract (arXiv)

Lack of transparency has been the Achilles heal of Neural Networks and their wider adoption in industry. Despite significant interest this shortcoming has not been adequately addressed. This study proposes a novel framework called Hide-and-Seek (HnS) for training Interpretable Neural Networks and establishes a theoretical foundation for exploring and comparing similar ideas. Extensive experimentation indicates that a high degree of interpretability can be imputed into Neural Networks, without sacrificing their predictive power.