English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

This paper presents an unsupervised method to learn a neural network, namelyan explainer, to interpret a pre-trained convolutional neural network (CNN),i.e., explaining knowledge representations hidden in middle conv-layers of theCNN. Given feature maps of a certain conv-layer of the CNN, the explainerperforms like an auto-encoder, which first disentangles the feature maps intoobject-part features and then inverts object-part features back to features ofhigher conv-layers of the CNN. More specifically, the explainer containsinterpretable conv-layers, where each filter disentangles the representation ofa specific object part from chaotic input feature maps. As a paraphrase of CNNfeatures, the disentangled representations of object parts help peopleunderstand the logic inside the CNN. We also learn the explainer to useobject-part features to reconstruct features of higher CNN layers, in order tominimize loss of information during the feature disentanglement. Morecrucially, we learn the explainer via network distillation without using anyannotations of sample labels, object parts, or textures for supervision. Wehave applied our method to different types of CNNs for evaluation, andexplainers have significantly boosted the interpretability of CNN features.

Unsupervised Learning of Neural Networks to Explain Neural Networks