Visualizing Deep Neural Network Decisions: Prediction Difference Analysis
Preprint
Abstract
This article presents the prediction difference analysis method for visualizing the response of a deep neural network to a specific input. When classifying images, the method highlights areas in a given input image that provide evidence for or against a certain class. It overcomes several shortcoming of previous methods and provides great additional insight into the decision making process of classifiers. Making neural network decisions interpretable through visualization is important both to improve models and to accelerate the adoption of black-box classifiers in application areas such as medicine. We illustrate the method in experiments on natural images (ImageNet data), as well as medical images (MRI brain scans).Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance PropagationPLOS ONE, 2015
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- A data‐centric neuroscience gateway: design, implementation, and experiencesConcurrency and Computation: Practice and Experience, 2014
- On the interpretation of weight vectors of linear models in multivariate neuroimagingNeuroImage, 2014
- Analytic estimation of statistical significance maps for support vector machine based multi-variate image analysis and classificationNeuroImage, 2013
- Describing the Brain in Autism in Five Dimensions—Magnetic Resonance Imaging-Assisted Diagnosis of Autism Spectrum Disorder Using a Multiparameter Classification ApproachThe Journal of Neuroscience, 2010
- Automatic classification of MR scans in Alzheimer's diseaseBrain, 2008
- Support vector machine learning-based fMRI data group analysisNeuroImage, 2007
- Classifying brain states and determining the discriminating activation patterns: Support Vector Machine on functional MRI dataNeuroImage, 2005