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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Beginning from a basic neural-network architecture, we test the potentialbenefits offered by a range of advanced techniques for machine learning, inparticular deep learning, in the context of a typical classification problemencountered in the domain of high-energy physics, using a well-studied dataset:the 2014 Higgs ML Kaggle dataset. The advantages are evaluated in terms of bothperformance metrics and the time required to train and apply the resultingmodels. Techniques examined include domain-specific data-augmentation, learningrate and momentum scheduling, (advanced) ensembling in both model-space andweight-space, and alternative architectures and connection methods. Followingthe investigation, we arrive at a model which achieves equal performance to thewinning solution of the original Kaggle challenge, whilst being significantlyquicker to train and apply, and being suitable for use with both GPU and CPUhardware setups. These reductions in timing and hardware requirementspotentially allow the use of more powerful algorithms in HEP analyses, wheremodels must be retrained frequently, sometimes at short notice, by small groupsof researchers with limited hardware resources. Additionally, a new wrapperlibrary for PyTorch called LUMIN is presented, which incorporates all of thetechniques studied.

machine learning: science and technology

On the impact of selected modern deep-learning techniques to the  performance and celerity of classification models in an experimental  high-energy physics use case