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

There is great interest in using formal methods to guarantee the reliabilityof deep neural networks. However, these techniques may also be used to implantcarefully selected input-output pairs. We present initial results on a noveltechnique for using SMT solvers to fine tune the weights of a ReLU neuralnetwork to guarantee outcomes on a finite set of particular examples. Thisprocedure can be used to ensure performance on key examples, but it could alsobe used to insert difficult-to-find incorrect examples that trigger unexpectedperformance. We demonstrate this approach by fine tuning an MNIST network toincorrectly classify a particular image and discuss the potential for theapproach to compromise reliability of freely-shared machine learning models.

Incorrect by Construction: Fine Tuning Neural Networks for Guaranteed Performance on Finite Sets of Examples