Learning how to explain neural networks: PatternNet and PatternAttribution
international conference on learning representations, 2018.
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 ...More
PPT (Upload PPT)