Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
Grégoire Montavon Sebastian Bach Alexander Binder Wojciech Samek and Klaus-Robert Müller Thanks: This work was supported by the Brain Korea 21 Plus Program through the National Research Foundation of Korea funded by the Ministry of Education. This work was also supported by the grant DFG (MU˜987/17-1) and by the German Ministry for Education and Research as Berlin Big Data Center BBDC (01IS14013A). This publication only reflects the authors views. Funding agencies are not liable for any use that may be made of the information contained herein. Asterisks indicate corresponding author. Thanks: $ˆ*$G. Montavon is with the Berlin Institute of Technology (TU Berlin), 10587 Berlin, Germany. (e-mail: Thanks: S. Bach is with Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany. (e-mail: Thanks: A. Binder is with the Singapore University of Technology and Design, 487372, Singapore. (e-mail: Thanks: $ˆ*$W. Samek is with Fraunhofer Heinrich Hertz Institute, 10587 Berlin, Germany. (e-mail: Thanks: $ˆ*$K.-R. Müller is with the Berlin Institute of Technology (TU Berlin), 10587 Berlin, Germany, and also with the Department of Brain and Cognitive Engineering, Korea University, Seoul 136-713, Korea (e-mail:
Abstract
Nonlinear methods such as Deep Neural Networks (DNNs) are the gold standard for various challenging machine learning problems, e.g., image classification, natural language processing or human action recognition. Although these methods perform impressively well, they have a significant disadvantage, the lack of transparency, limiting the interpretability of the solution and thus the scope of application in practice. Especially DNNs act as black boxes due to their multilayer nonlinear structure. In this paper we introduce a novel methodology for interpreting generic multilayer neural networks by decomposing the network classification decision into contributions of its input elements. Although our focus is on image classification, the method is applicable to a broad set of input data, learning tasks and network architectures. Our method is based on deep Taylor decomposition and efficiently utilizes the structure of the network by backpropagating the explanations from the output to the input layer. We evaluate the proposed method empirically on the MNIST and ILSVRC data sets.
原文 arXiv:1512.02479;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1512.02479v1