Your deep learning model does not need to be a black box.

**Have you checked the [list of proposed rules](https://github.com/Benjamin-Lee/deep-rules/issues?q=is%3Aissue+is%3Aopen+label%3Arule) to see if the rule has already been proposed?**

- [x] Yes

Many machine learning application tolerate black-box models; however, research in Life Sciences benefits from details that come from the model interpretation. The idea of this rule is to describe the use of methods, focusing on autoencoders, as a way to interpret you deep learning model.

**Any citations for the rule?** (peer-reviewed literature preferred but not required)
- [Understanding Random Forests: From Theory to Practice](https://arxiv.org/abs/1407.7502): not deep learn, but relevant.
- [Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning](https://doi.org/10.1038/nbt.3300)
- [Visual Interpretability for Deep Learning: a Survey](https://arxiv.org/abs/1802.00614)

Review the proposed-rules list and the cited literature, especially the sources on deep-learning interpretability and autoencoders. Clarify the rule's scope and wording with maintainers; done means an agreed, citable rule describing model-interpretation methods for life-science applications.

Written by the indexing model from the issue text.