Matches in SemOpenAlex for { <https://semopenalex.org/work/W4221036131> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W4221036131 abstract "Sound localization is the ability of humans to determine the source direction of sounds that they hear. Emulating this capability in virtual environments can have various societally relevant applications enabling more realistic virtual acoustics. We use a variety of artificial intelligence methods, such as machine learning via an Artificial Neural Network (ANN) model, to emulate human sound localization abilities. This paper addresses the particular challenge that the training and optimization of these models is very computationally-intensive when working with audio signal datasets. It describes the successful porting of our novel ANN model code for sound localization from limiting serial CPU-based systems to powerful, cutting-edge High-Performance Computing (HPC) resources to obtain significant speed-ups of the training and optimization process. Selected details of the code refactoring and HPC porting are described, such as adapting hyperparameter optimization algorithms to efficiently use the available HPC resources and replacing third-party libraries responsible for audio signal analysis and linear algebra. This study demonstrates that using innovative HPC systems at the Jülich Supercomputing Centre, equipped with high-tech Graphics Processing Unit (GPU) resources and based on the Modular Supercomputing Architecture, enables significant speed-ups and reduces the time-to-solution for sound localization from three days to three hours per ANN model." @default.
- W4221036131 created "2022-04-03" @default.
- W4221036131 creator A5008220787 @default.
- W4221036131 creator A5012635400 @default.
- W4221036131 creator A5031081327 @default.
- W4221036131 creator A5070119351 @default.
- W4221036131 creator A5072364516 @default.
- W4221036131 date "2022-02-16" @default.
- W4221036131 modified "2023-09-26" @default.
- W4221036131 title "Speed-Up of Machine Learning for Sound Localization via High-Performance Computing" @default.
- W4221036131 cites W2009896906 @default.
- W4221036131 cites W2059919683 @default.
- W4221036131 cites W2080101027 @default.
- W4221036131 cites W2191779130 @default.
- W4221036131 cites W2622609602 @default.
- W4221036131 cites W2766736793 @default.
- W4221036131 cites W2949676527 @default.
- W4221036131 cites W3081424945 @default.
- W4221036131 cites W3099878876 @default.
- W4221036131 doi "https://doi.org/10.1109/it54280.2022.9743519" @default.
- W4221036131 hasPublicationYear "2022" @default.
- W4221036131 type Work @default.
- W4221036131 citedByCount "2" @default.
- W4221036131 countsByYear W42210361312022 @default.
- W4221036131 crossrefType "proceedings-article" @default.
- W4221036131 hasAuthorship W4221036131A5008220787 @default.
- W4221036131 hasAuthorship W4221036131A5012635400 @default.
- W4221036131 hasAuthorship W4221036131A5031081327 @default.
- W4221036131 hasAuthorship W4221036131A5070119351 @default.
- W4221036131 hasAuthorship W4221036131A5072364516 @default.
- W4221036131 hasBestOaLocation W42210361312 @default.
- W4221036131 hasConcept C104267543 @default.
- W4221036131 hasConcept C106251023 @default.
- W4221036131 hasConcept C111919701 @default.
- W4221036131 hasConcept C113775141 @default.
- W4221036131 hasConcept C118524514 @default.
- W4221036131 hasConcept C154945302 @default.
- W4221036131 hasConcept C173608175 @default.
- W4221036131 hasConcept C2777904410 @default.
- W4221036131 hasConcept C2778119891 @default.
- W4221036131 hasConcept C2779851693 @default.
- W4221036131 hasConcept C2781335571 @default.
- W4221036131 hasConcept C41008148 @default.
- W4221036131 hasConcept C50644808 @default.
- W4221036131 hasConcept C83283714 @default.
- W4221036131 hasConcept C84462506 @default.
- W4221036131 hasConcept C9390403 @default.
- W4221036131 hasConcept C98045186 @default.
- W4221036131 hasConceptScore W4221036131C104267543 @default.
- W4221036131 hasConceptScore W4221036131C106251023 @default.
- W4221036131 hasConceptScore W4221036131C111919701 @default.
- W4221036131 hasConceptScore W4221036131C113775141 @default.
- W4221036131 hasConceptScore W4221036131C118524514 @default.
- W4221036131 hasConceptScore W4221036131C154945302 @default.
- W4221036131 hasConceptScore W4221036131C173608175 @default.
- W4221036131 hasConceptScore W4221036131C2777904410 @default.
- W4221036131 hasConceptScore W4221036131C2778119891 @default.
- W4221036131 hasConceptScore W4221036131C2779851693 @default.
- W4221036131 hasConceptScore W4221036131C2781335571 @default.
- W4221036131 hasConceptScore W4221036131C41008148 @default.
- W4221036131 hasConceptScore W4221036131C50644808 @default.
- W4221036131 hasConceptScore W4221036131C83283714 @default.
- W4221036131 hasConceptScore W4221036131C84462506 @default.
- W4221036131 hasConceptScore W4221036131C9390403 @default.
- W4221036131 hasConceptScore W4221036131C98045186 @default.
- W4221036131 hasFunder F4320335254 @default.
- W4221036131 hasLocation W42210361311 @default.
- W4221036131 hasLocation W42210361312 @default.
- W4221036131 hasOpenAccess W4221036131 @default.
- W4221036131 hasPrimaryLocation W42210361311 @default.
- W4221036131 hasRelatedWork W2030707850 @default.
- W4221036131 hasRelatedWork W2108266785 @default.
- W4221036131 hasRelatedWork W2123057625 @default.
- W4221036131 hasRelatedWork W2732971278 @default.
- W4221036131 hasRelatedWork W3213915833 @default.
- W4221036131 hasRelatedWork W4210369363 @default.
- W4221036131 hasRelatedWork W4210909429 @default.
- W4221036131 hasRelatedWork W4221036131 @default.
- W4221036131 hasRelatedWork W4226161603 @default.
- W4221036131 hasRelatedWork W4226437700 @default.
- W4221036131 isParatext "false" @default.
- W4221036131 isRetracted "false" @default.
- W4221036131 workType "article" @default.