LICON: A Linear Weighting Scheme for the Contribution ofInput Variables in Deep Artificial Neural Networks.
CIKM'16: ACM Conference on Information and Knowledge Management Indianapolis Indiana USA October, 2016(2016)
摘要
In recent years artificial neural networks have become the method of choice for many pattern recognition tasks. Despite their overwhelming success, a rigorous and easy to interpret mathematical explanation of the influence of input variables on a output produced by a neural network is still missing.
We propose a generic framework as well as a concrete method for quantifying the influence of individual input signals on the output computed by a deep neural network. Inspired by the variable weighting scheme in the log-linear combination of variables in logistic regression, the proposed method provides linear models for specific observations of the input variables. This linear model locally approximates the behaviour of the neural network and can be used to quantify the influence of input variables in a principled way. We demonstrate the effectiveness of the proposed method in experiments on various synthetic and real-world datasets.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络