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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Neural networks are a powerful class of non-linear functions. However, theirblack-box nature makes it difficult to explain their behaviour and certifytheir safety. Abstraction techniques address this challenge by transforming theneural network into a simpler, over-approximated function. Unfortunately,existing abstraction techniques are slack, which limits their applicability tosmall local regions of the input domain. In this paper, we propose GlobalInterval Neural Network Abstractions with Center-Exact Reconstruction(GINNACER). Our novel abstraction technique produces sound over-approximationbounds over the whole input domain while guaranteeing exact reconstructions forany given local input. Our experiments show that GINNACER is several orders ofmagnitude tighter than state-of-the-art global abstraction techniques, whilebeing competitive with local ones.

Towards Global Neural Network Abstractions with Locally-Exact Reconstruction