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

State-of-the-art techniques for enhancing robustness of deep networks mostlyrely on empirical risk minimization with suitable data augmentation. In thispaper, we propose a complementary approach motivated by communication theory,aimed at enhancing the signal-to-noise ratio at the output of a neural networklayer via neural competition during learning and inference. In addition tominimization of a standard end-to-end cost, neurons compete to sparselyrepresent layer inputs by maximization of a tilted exponential (TEXP) objectivefunction for the layer. TEXP learning can be interpreted as maximum likelihoodestimation of matched filters under a Gaussian model for data noise. Inferencein a TEXP layer is accomplished by replacing batch norm by a tilted softmax,which can be interpreted as computation of posterior probabilities for thecompeting signaling hypotheses represented by each neuron. After providinginsights via simplified models, we show, by experimentation on standard imagedatasets, that TEXP learning and inference enhances robustness against noiseand other common corruptions, without requiring data augmentation. Furthercumulative gains in robustness against this array of distortions can beobtained by appropriately combining TEXP with data augmentation techniques.

Improving Robustness via Tilted Exponential Layer: A Communication-Theoretic Perspective