# Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation

arXiv: https://arxiv.org/abs/1611.08191 · HTML: https://mlsanity.com/paper/1611.08191/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2016.

## Built on by (most cited first, 11 of 11)

- [Explanations in Autonomous Driving: A Survey](https://mlsanity.com/paper/2103.05154/) (2021)
- [Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions](https://mlsanity.com/paper/2112.11561/) (2021)
- [Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geoscience](https://mlsanity.com/paper/2202.03407/) (2022)
- [Knowledge-intensive Language Understanding for Explainable AI](https://mlsanity.com/paper/2108.01174/) (2021)
- [Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Dataset](https://mlsanity.com/paper/2103.10005/) (2021)
- [A Practical guide on Explainable AI Techniques applied on Biomedical use case applications](https://mlsanity.com/paper/2111.14260/) (2021)
- [Learning phases with Quantum Monte Carlo simulation cell](https://mlsanity.com/paper/2503.23098/) (2025)
- [AdjointBackMapV2: Precise Reconstruction of Arbitrary CNN Unit's Activation via Adjoint Operators](https://mlsanity.com/paper/2110.01736/) (2021)
- [Interpretable Feature Learning Framework for Smoking Behavior Detection](https://mlsanity.com/paper/2112.08178/) (2021)
- [FedSub: Introducing Class-aware Subnetworks Fusion to Enhance Personalized Federated Learning](https://mlsanity.com/paper/2411.08699/) (2024)
- [A Novel Multimodal RUL Framework for Remaining Useful Life Estimation with Layer-wise Explanations](https://mlsanity.com/paper/2512.06708/) (2025)

## Abstract (arXiv)

Complex nonlinear models such as deep neural network (DNNs) have become an important tool for image classification, speech recognition, natural language processing, and many other fields of application. These models however lack transparency due to their complex nonlinear structure and to the complex data distributions to which they typically apply. As a result, it is difficult to fully characterize what makes these models reach a particular decision for a given input. This lack of transparency can be a drawback, especially in the context of sensitive applications such as medical analysis or security. In this short paper, we summarize a recent technique introduced by Bach et al. [1] that explains predictions by decomposing the classification decision of DNN models in terms of input variables.