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

We present a sparse representation of model uncertainty for Deep NeuralNetworks (DNNs) where the parameter posterior is approximated with an inverseformulation of the Multivariate Normal Distribution (MND), also known as theinformation form. The key insight of our work is that the information matrix,i.e. the inverse of the covariance matrix tends to be sparse in its spectrum.Therefore, dimensionality reduction techniques such as low rank approximations(LRA) can be effectively exploited. To achieve this, we develop a novelsparsification algorithm and derive a cost-effective analytical sampler. As aresult, we show that the information form can be scalably applied to representmodel uncertainty in DNNs. Our exhaustive theoretical analysis and empiricalevaluations on various benchmarks show the competitiveness of our approach overthe current methods.

Estimating Model Uncertainty of Neural Networks in Sparse Information Form