# Detecting Deep Neural Network Defects with Data Flow Analysis

arXiv: https://arxiv.org/abs/1909.02190 · HTML: https://mlsanity.com/paper/1909.02190/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2019.

## Built on by (most cited first, 2 of 2)

- [Towards Training Reproducible Deep Learning Models](https://mlsanity.com/paper/2202.02326/) (2022)
- [HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations](https://mlsanity.com/paper/2205.15479/) (2022)

## Abstract (arXiv)

Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks. However, it is very hard to figure out whether the low precision of a DNN model is an inevitable result, or caused by defects. This paper aims at addressing this challenging problem. We find that the internal data flow footprints of a DNN model can provide insights to locate the root cause effectively. We develop DeepMorph (DNN Tomography) to analyze the root cause, which can guide a DNN developer to improve the model.