WS 2017/18

Explaining Neural Networks with Layerwise Relevance Propagation (LRP)

The project was focused on the problem of explaining Neural Network Decisions with LRP method. Student analyzed interpretations of the CNN-based classification and aggregated results for the MNIST dataset. Also, students applied LRP to the Fashion MNIST dataset from Zalando and presented observed results in the presentation. You can try out the Demo here.

Interactive Named Entity Recognition