Learning how to explain neural networks: PatternNet and PatternAttributionDownload PDF

15 Feb 2018 (modified: 16 Jun 2024)ICLR 2018 Conference Blind SubmissionReaders: Everyone
Abstract: DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. Yet they are used on multi-layer networks with millions of parameters. This is a cause for concern since linear models are simple neural networks. We argue that explanation methods for neural nets should work reliably in the limit of simplicity, the linear models. Based on our analysis of linear models we propose a generalization that yields two explanation techniques (PatternNet and PatternAttribution) that are theoretically sound for linear models and produce improved explanations for deep networks.
TL;DR: Without learning, it is impossible to explain a machine learning model's decisions.
Keywords: machine learning, interpretability, deep learning
Code: [![Papers with Code](/images/pwc_icon.svg) 3 community implementations](https://paperswithcode.com/paper/?openreview=Hkn7CBaTW)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1705.05598/code)
13 Replies

Loading