Explaining Neural Networks Semantically and Quantitatively [article]

Runjin Chen, Hao Chen, Ge Huang, Jie Ren, Quanshi Zhang
2018 arXiv   pre-print
This paper presents a method to explain the knowledge encoded in a convolutional neural network (CNN) quantitatively and semantically. The analysis of the specific rationale of each prediction made by the CNN presents a key issue of understanding neural networks, but it is also of significant practical values in certain applications. In this study, we propose to distill knowledge from the CNN into an explainable additive model, so that we can use the explainable model to provide a quantitative
more » ... xplanation for the CNN prediction. We analyze the typical bias-interpreting problem of the explainable model and develop prior losses to guide the learning of the explainable additive model. Experimental results have demonstrated the effectiveness of our method.
arXiv:1812.07169v1 fatcat:e3d4cgdc6zhxndndvkkh24hhhq