PatternNet and PatternLRP - Improving the interpretability of neural networks

Deep learning has significantly advanced the state of the art in machine learning. However, neural networks are often considered black boxes. There is significant effort to develop techniques that explain a classifier's decisions. Although some of these approaches have resulted in compelling visualisations, there is a lack of theory of what is actually explained. Here we present an analysis of these methods and formulate a quality criterion for explanation methods. On this ground, we propose an improved method that may serve as an extension for existing back-projection and decomposition techniques.

[1]  Thomas Brox,et al.  Synthesizing the preferred inputs for neurons in neural networks via deep generator networks , 2016, NIPS.

[2]  Shane Legg,et al.  Human-level control through deep reinforcement learning , 2015, Nature.

[3]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[4]  Max Welling,et al.  Visualizing Deep Neural Network Decisions: Prediction Difference Analysis , 2017, ICLR.

[5]  Rob Fergus,et al.  Visualizing and Understanding Convolutional Networks , 2013, ECCV.

[6]  Andrew Zisserman,et al.  Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps , 2013, ICLR.

[7]  Motoaki Kawanabe,et al.  How to Explain Individual Classification Decisions , 2009, J. Mach. Learn. Res..

[8]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[9]  Razvan Pascanu,et al.  Theano: A CPU and GPU Math Compiler in Python , 2010, SciPy.

[10]  Alexander Binder,et al.  Explaining nonlinear classification decisions with deep Taylor decomposition , 2015, Pattern Recognit..

[11]  Jürgen Schmidhuber.  Deep Learning , 2017, Encyclopedia of Machine Learning and Data Mining.

[12]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[13]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

[14]  Stefan Haufe,et al.  On the interpretation of weight vectors of linear models in multivariate neuroimaging , 2014, NeuroImage.

[15]  Demis Hassabis,et al.  Mastering the game of Go with deep neural networks and tree search , 2016, Nature.

[16]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[17]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[18]  Alexander Binder,et al.  Evaluating the Visualization of What a Deep Neural Network Has Learned , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[19]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[20]  Hod Lipson,et al.  Understanding Neural Networks Through Deep Visualization , 2015, ArXiv.

[21]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.