FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3021337204> ?p ?o ?g. }

• W3021337204 endingPage "045006" @default.
• W3021337204 startingPage "045006" @default.
• W3021337204 abstract "Beginning from a basic neural-network architecture, we test the potential benefits offered by a range of advanced techniques for machine learning, in particular deep learning, in the context of a typical classification problem encountered 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 both performance metrics and the time required to train and apply the resulting models. Techniques examined include domain-specific data-augmentation, learning rate and momentum scheduling, (advanced) ensembling in both model-space and weight-space, and alternative architectures and connection methods. Following the investigation, we arrive at a model which achieves equal performance to the winning solution of the original Kaggle challenge, whilst being significantly quicker to train and apply, and being suitable for use with both GPU and CPU hardware setups. These reductions in timing and hardware requirements potentially allow the use of more powerful algorithms in HEP analyses, where models must be retrained frequently, sometimes at short notice, by small groups of researchers with limited hardware resources. Additionally, a new wrapper library for PyTorch called LUMIN is presented, which incorporates all of the techniques studied." @default.
• W3021337204 created "2020-05-13" @default.
• W3021337204 creator A5045198005 @default.
• W3021337204 date "2020-09-19" @default.
• W3021337204 modified "2023-09-23" @default.
• W3021337204 title "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" @default.
• W3021337204 cites W1498436455 @default.
• W3021337204 cites W1677182931 @default.
• W3021337204 cites W1858542512 @default.
• W3021337204 cites W1987435915 @default.
• W3021337204 cites W1997580096 @default.
• W3021337204 cites W2001619934 @default.
• W3021337204 cites W2004915807 @default.
• W3021337204 cites W2011301426 @default.
• W3021337204 cites W2016833372 @default.
• W3021337204 cites W2041688602 @default.
• W3021337204 cites W2119388406 @default.
• W3021337204 cites W2128158076 @default.
• W3021337204 cites W2128881154 @default.
• W3021337204 cites W2131021228 @default.
• W3021337204 cites W2135046866 @default.
• W3021337204 cites W2143467729 @default.
• W3021337204 cites W2146292423 @default.
• W3021337204 cites W2148483295 @default.
• W3021337204 cites W2149591630 @default.
• W3021337204 cites W2165698076 @default.
• W3021337204 cites W2167727518 @default.
• W3021337204 cites W2168135588 @default.
• W3021337204 cites W2194775991 @default.
• W3021337204 cites W2223576019 @default.
• W3021337204 cites W2342249984 @default.
• W3021337204 cites W2395579298 @default.
• W3021337204 cites W2508075755 @default.
• W3021337204 cites W2752782242 @default.
• W3021337204 cites W2798474886 @default.
• W3021337204 cites W2807858310 @default.
• W3021337204 cites W2810437889 @default.
• W3021337204 cites W2911964244 @default.
• W3021337204 cites W2913867985 @default.
• W3021337204 cites W2949905295 @default.
• W3021337204 cites W2963446712 @default.
• W3021337204 cites W2964054038 @default.
• W3021337204 cites W2981025103 @default.
• W3021337204 cites W3002851826 @default.
• W3021337204 cites W3006943238 @default.
• W3021337204 cites W3098229010 @default.
• W3021337204 cites W3102476541 @default.
• W3021337204 cites W3103170771 @default.
• W3021337204 cites W3103589224 @default.
• W3021337204 cites W3104690326 @default.
• W3021337204 cites W3121642222 @default.
• W3021337204 cites W4232091795 @default.
• W3021337204 doi "https://doi.org/10.1088/2632-2153/ab983a" @default.
• W3021337204 hasPublicationYear "2020" @default.
• W3021337204 type Work @default.
• W3021337204 sameAs 3021337204 @default.
• W3021337204 citedByCount "4" @default.
• W3021337204 countsByYear W30213372042021 @default.
• W3021337204 crossrefType "journal-article" @default.
• W3021337204 hasAuthorship W3021337204A5045198005 @default.
• W3021337204 hasBestOaLocation W30213372041 @default.
• W3021337204 hasConcept C108583219 @default.
• W3021337204 hasConcept C119857082 @default.
• W3021337204 hasConcept C127413603 @default.
• W3021337204 hasConcept C134306372 @default.
• W3021337204 hasConcept C151730666 @default.
• W3021337204 hasConcept C154945302 @default.
• W3021337204 hasConcept C17744445 @default.
• W3021337204 hasConcept C199539241 @default.
• W3021337204 hasConcept C206729178 @default.
• W3021337204 hasConcept C21547014 @default.
• W3021337204 hasConcept C2779343474 @default.
• W3021337204 hasConcept C2779913896 @default.
• W3021337204 hasConcept C33923547 @default.
• W3021337204 hasConcept C36503486 @default.
• W3021337204 hasConcept C41008148 @default.
• W3021337204 hasConcept C50644808 @default.
• W3021337204 hasConcept C86803240 @default.
• W3021337204 hasConceptScore W3021337204C108583219 @default.
• W3021337204 hasConceptScore W3021337204C119857082 @default.
• W3021337204 hasConceptScore W3021337204C127413603 @default.
• W3021337204 hasConceptScore W3021337204C134306372 @default.
• W3021337204 hasConceptScore W3021337204C151730666 @default.
• W3021337204 hasConceptScore W3021337204C154945302 @default.
• W3021337204 hasConceptScore W3021337204C17744445 @default.
• W3021337204 hasConceptScore W3021337204C199539241 @default.
• W3021337204 hasConceptScore W3021337204C206729178 @default.
• W3021337204 hasConceptScore W3021337204C21547014 @default.
• W3021337204 hasConceptScore W3021337204C2779343474 @default.
• W3021337204 hasConceptScore W3021337204C2779913896 @default.
• W3021337204 hasConceptScore W3021337204C33923547 @default.
• W3021337204 hasConceptScore W3021337204C36503486 @default.
• W3021337204 hasConceptScore W3021337204C41008148 @default.
• W3021337204 hasConceptScore W3021337204C50644808 @default.
• W3021337204 hasConceptScore W3021337204C86803240 @default.
• W3021337204 hasIssue "4" @default.
• W3021337204 hasLocation W30213372041 @default.
• W3021337204 hasLocation W30213372042 @default.

• next