CVDec 7, 2017
Network Analysis for Explanation
arXiv:1712.02890v13 citations
Originality Synthesis-oriented
AI Analysis
This work addresses the need for explainable AI in safety-critical domains, but appears incremental as it builds on existing network analysis techniques.
The paper tackled the problem of explainability in AI for safety-critical systems by analyzing trained networks to identify key inference-contributing features and developing a method to generate explanations for inference processes.
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.