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

A recent trend in explainable AI research has focused on surrogate modeling,where neural networks are approximated as simpler ML algorithms such as kernelmachines. A second trend has been to utilize kernel functions in variousexplain-by-example or data attribution tasks to investigate a diverse set ofneural network behavior. In this work, we combine these two trends to analyzeapproximate empirical neural tangent kernels (eNTK) for data attribution.Approximation is critical for eNTK analysis due to the high computational costto compute the eNTK. We define new approximate eNTK and perform novel analysison how well the resulting kernel machine surrogate models correlate with theunderlying neural network. We introduce two new random projection variants ofapproximate eNTK which allow users to tune the time and memory complexity oftheir calculation. We conclude that kernel machines using approximate neuraltangent kernel as the kernel function are effective surrogate models, with theintroduced trace NTK the most consistent performer.

Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models