Explaining the Decisions of Convolutional and Recurrent Neural Networks
Wojciech Samek, Leila Arras, Ahmed Osman, Grégoire Montavon, Klaus‐Robert Müller · Cambridge University Press eBooks · 2022
In this chapter we discuss the algorithmic and theoretical underpinnings of layer-wise relevance propagation (LRP), apply the method to a complex model trained for the task of visual question answering (VQA), and demonstrate that it produces meaningful explanations, revealing interesting details about the model’s reasoning. We conclude the chapter by commenting on the general limitations of current explanation techniques and interesting future directions.