Network Analysis for Explanation
arXiv:1712.02890
Abstract
Safety critical systems strongly require the quality aspects of artificial intelligence including explainability. In this paper, we analyzed a trained network to extract features which mainly contribute the inference. Based on the analysis, we developed a simple solution to generate explanations of the inference processes.
References in corpus (5)
- Distributed Representations of Words and Phrases and their Compositionality
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
- Not Just a Black Box: Learning Important Features Through Propagating Activation Differences
- Theano-based Large-Scale Visual Recognition with Multiple GPUs