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

In this paper, we present Deep Extreme Feature Extraction (DEFE), a newensemble MVA method for searching $\tau^{+}\tau^{-}$ channel of Higgs bosons inhigh energy physics. DEFE can be viewed as a deep ensemble learning scheme thattrains a strongly diverse set of neural feature learners without explicitlyencouraging diversity and penalizing correlations. This is achieved by adoptingan implicit neural controller (not involved in feedforward compuation) thatdirectly controls and distributes gradient flows from higher level deepprediction network. Such model-independent controller results in that everysingle local feature learned are used in the feature-to-output mapping stage,avoiding the blind averaging of features. DEFE makes the ensembles 'deep' inthe sense that it allows deep post-process of these features that tries tolearn to select and abstract the ensemble of neural feature learners. With theapplication of this model, a selection regions full of signal process can beobtained through the training of a miniature collision events set. Incomparison of the Classic Deep Neural Network, DEFE shows a state-of-the-artperformance: the error rate has decreased by about 37\%, the accuracy hasbroken through 90\% for the first time, along with the discovery significancehas reached a standard deviation of 6.0 $\sigma$. Experimental data shows that,DEFE is able to train an ensemble of discriminative feature learners thatboosts the overperformance of final prediction.

Deep Extreme Feature Extraction: New MVA Method for Searching Particles in High Energy Physics