**Layer-wise Relevance Propagation (LRP)
**

By Prof. Hyunseok Oh

https://sddo.gist.ac.kr/

SDDO Lab at GIST

https://sddo.gist.ac.kr/

SDDO Lab at GIST

Reference for this contents

- Deep learning is a 'black-box' model that cannot be interpreted by users.
- We need to figure out "why" does the model arrive at a certain prediction.

- Interpreting models: how to interpret the model itself
- Explaining decisions: how to figure out why the decision was made.

- LRP is a technique that describes the decision boundary of model by applying Taylor decomposition.
- As its name implies, the relevance $R(x)$ that contributed to the prediction results is calculated and propagated for each layer.
- That is, LRP can check the influence of each pixel of the input layer on the prediction results.

The basic assumptions and how LRP works are as follows:

- Each neuron has a certain relevance.
- The relevance is redistributed from the output to the input of each neuron.
- The relevance is preserved when redistributed to each layer.