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

This paper considers the problem of sequential fusion of predictions fromneural networks (NN) and fusion of predictions from multiple NN. This fusionstrategy increases the robustness, i.e., reduces the impact of one incorrectclassification and detection of outliers the \nn has not seen during training.This paper uses Laplacian approximation of Bayesian NNs (BNNs) to quantify theuncertainty necessary for fusion. Here, an extension is proposed such that theprediction of the NN can be represented by multimodal distributions. Regardingcalibration of the estimated uncertainty in the prediction, the performance issignificantly improved by having the flexibility to represent a multimodaldistribution. Two class classical image classification tasks, i.e., MNIST andCFAR10, and image sequences from camera traps of carnivores in Swedish forestshave been used to demonstrate the fusion strategies and proposed extension tothe Laplacian approximation.

Fusion framework and multimodality for the Laplacian approximation of Bayesian neural networks