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

We study the effects of constrained optimization formulations and Frank-Wolfealgorithms for obtaining interpretable neural network predictions.Reformulating the Rate-Distortion Explanations (RDE) method for relevanceattribution as a constrained optimization problem provides precise control overthe sparsity of relevance maps. This enables a novel multi-rate as well as arelevance-ordering variant of RDE that both empirically outperform standard RDEand other baseline methods in a well-established comparison test. We showcaseseveral deterministic and stochastic variants of the Frank-Wolfe algorithm andtheir effectiveness for RDE.

Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings