Deep Taylor Decomposition of Neural Networks

By egoire Montavon, Sebastian Bach, Alexander Binder, Wojciech Samek, Klaus{robert M Uller. 2016

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Erico Tjoa
2. Cuntai Guan
3. Constantin Waubert de Puiseau
4. Richard Meyes
5. Andres Felipe Posada-Moreno
6. Tobias Meisen
7. Fabien Lotte

Citations in the corpus

• A Survey on Explainable Artificial Intelligence (XAI): Toward Medical XAI (2019, methodology): “Other decomposition methods further developed include Deep Taylor Decomposition [44], DeepLIFT and gradient*input [45], Prediction Difference Analysis [46].”
• Under the Hood of Neural Networks: Characterizing Learned Representations by Functional Neuron Populations and Network Ablations (2020, background): “, 2016), deep taylor decomposition (Montavon et al., 2016) and class-enhanced attentive response (CLEAR) (Kumar et al.”