Skip to content Skip to navigation

Interpreting deep neural networks by explaining their predictions - Wojciech Samek

Stanford Neurosciences Institute, Wojciech Samek
August 9, 2018 - 11:30am
Jordan Hall, Room 120

Interpreting Deep Neural Networks by Explaining their Predictions

Wojciech Samek

Fraunhofer Heinrich Hertz Institute in Berlin


Deep neural networks (DNNs) are reaching or even exceeding the human level on an increasing number of complex tasks. However, due to their complex non-linear structure, these models are usually applied in a black box manner, i.e., no information is provided about what exactly makes them arrive at their predictions. This lack of transparency can be a major drawback in practice.  In my talk I will present a general technique, Layer-wise Relevance Propagation (LRP), for interpreting DNNs by explaining their predictions. I will demonstrate the effectivity of LRP when applied to various datatypes (images, text, audio, video, EEG/fMRI signals) and neural architectures (ConvNets, LSTMs), and will summarize what we have learned so far by peering inside these black boxes.

Event Sponsor: 
Vision Breakfast (Psychology Department)
Contact Email: 
Mareike Grotheer <>

This event is part of: