Tuning of Mixture-of-Experts Mixed-Precision Neural Networks Article Swipe
Deep learning has become a useful data analysis method, however mainstream adaption in distributed computer software and embedded devices has been low so far. Often, adding deep learning inference in mainstream applications and devices requires new hardware with signal processors suited for convolutional neural networks. This work adds new data types (quantized 16-bit and 8-bit integer, 16-bit floating point) to Caffe in order to save memory and increase inference speed on existing commodity graphics processors with OpenCL, common in everyday devices. Existing models can be executed effortlessly in mixed-precision mode. Additionally, we propose a variation of mixture-of-experts to increase inference speed on AlexNet for image classification. We managed to decrease memory usage up to 3.29x while increasing inference speed up to 3.01x on certain devices. We demonstrate with five simple examples how the presented techniques can easily be applied to different machine learning problems. The whole pipeline, consisting of models, example python scripts and modified Caffe library, is available as Open Source software.
Related Topics
Concepts
Computer science
Deep learning
Python (programming language)
Inference
Convolutional neural network
Artificial intelligence
Artificial neural network
Software
Pipeline (software)
Computer engineering
Speedup
Scripting language
Graphics pipeline
Machine learning
Computer architecture
Parallel computing
Programming language
Computer graphics
3D computer graphics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2209.15427
- https://arxiv.org/pdf/2209.15427
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4300980405
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4300980405Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2209.15427Digital Object Identifier
- Title
-
Tuning of Mixture-of-Experts Mixed-Precision Neural NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-09-29Full publication date if available
- Authors
-
Fabian TschoppList of authors in order
- Landing page
-
https://arxiv.org/abs/2209.15427Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2209.15427Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2209.15427Direct OA link when available
- Concepts
-
Computer science, Deep learning, Python (programming language), Inference, Convolutional neural network, Artificial intelligence, Artificial neural network, Software, Pipeline (software), Computer engineering, Speedup, Scripting language, Graphics pipeline, Machine learning, Computer architecture, Parallel computing, Programming language, Computer graphics, 3D computer graphicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4300980405 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2209.15427 |
| ids.doi | https://doi.org/10.48550/arxiv.2209.15427 |
| ids.openalex | https://openalex.org/W4300980405 |
| fwci | |
| type | preprint |
| title | Tuning of Mixture-of-Experts Mixed-Precision Neural Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10320 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9976000189781189 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/1702 |
| topics[0].subfield.display_name | Artificial Intelligence |
| topics[0].display_name | Neural Networks and Applications |
| topics[1].id | https://openalex.org/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9886000156402588 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Neural Network Applications |
| topics[2].id | https://openalex.org/T11206 |
| topics[2].field.id | https://openalex.org/fields/31 |
| topics[2].field.display_name | Physics and Astronomy |
| topics[2].score | 0.9598000049591064 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/3109 |
| topics[2].subfield.display_name | Statistical and Nonlinear Physics |
| topics[2].display_name | Model Reduction and Neural Networks |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.8536735773086548 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C108583219 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6415153741836548 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[1].display_name | Deep learning |
| concepts[2].id | https://openalex.org/C519991488 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6359701156616211 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q28865 |
| concepts[2].display_name | Python (programming language) |
| concepts[3].id | https://openalex.org/C2776214188 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6062120795249939 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[3].display_name | Inference |
| concepts[4].id | https://openalex.org/C81363708 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5820865035057068 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[4].display_name | Convolutional neural network |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.5626733303070068 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C50644808 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5484106540679932 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[6].display_name | Artificial neural network |
| concepts[7].id | https://openalex.org/C2777904410 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5356582999229431 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7397 |
| concepts[7].display_name | Software |
| concepts[8].id | https://openalex.org/C43521106 |
| concepts[8].level | 2 |
| concepts[8].score | 0.5073661208152771 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2165493 |
| concepts[8].display_name | Pipeline (software) |
| concepts[9].id | https://openalex.org/C113775141 |
| concepts[9].level | 1 |
| concepts[9].score | 0.45627278089523315 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q428691 |
| concepts[9].display_name | Computer engineering |
| concepts[10].id | https://openalex.org/C68339613 |
| concepts[10].level | 2 |
| concepts[10].score | 0.4355561435222626 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1549489 |
| concepts[10].display_name | Speedup |
| concepts[11].id | https://openalex.org/C61423126 |
| concepts[11].level | 2 |
| concepts[11].score | 0.4304814338684082 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q187432 |
| concepts[11].display_name | Scripting language |
| concepts[12].id | https://openalex.org/C173552908 |
| concepts[12].level | 4 |
| concepts[12].score | 0.4191593527793884 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q1366289 |
| concepts[12].display_name | Graphics pipeline |
| concepts[13].id | https://openalex.org/C119857082 |
| concepts[13].level | 1 |
| concepts[13].score | 0.4104394018650055 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[13].display_name | Machine learning |
| concepts[14].id | https://openalex.org/C118524514 |
| concepts[14].level | 1 |
| concepts[14].score | 0.3205186128616333 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q173212 |
| concepts[14].display_name | Computer architecture |
| concepts[15].id | https://openalex.org/C173608175 |
| concepts[15].level | 1 |
| concepts[15].score | 0.24629586935043335 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q232661 |
| concepts[15].display_name | Parallel computing |
| concepts[16].id | https://openalex.org/C199360897 |
| concepts[16].level | 1 |
| concepts[16].score | 0.21547934412956238 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[16].display_name | Programming language |
| concepts[17].id | https://openalex.org/C77660652 |
| concepts[17].level | 2 |
| concepts[17].score | 0.21244144439697266 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q150971 |
| concepts[17].display_name | Computer graphics |
| concepts[18].id | https://openalex.org/C66629338 |
| concepts[18].level | 3 |
| concepts[18].score | 0.16258496046066284 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q189177 |
| concepts[18].display_name | 3D computer graphics |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.8536735773086548 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/deep-learning |
| keywords[1].score | 0.6415153741836548 |
| keywords[1].display_name | Deep learning |
| keywords[2].id | https://openalex.org/keywords/python |
| keywords[2].score | 0.6359701156616211 |
| keywords[2].display_name | Python (programming language) |
| keywords[3].id | https://openalex.org/keywords/inference |
| keywords[3].score | 0.6062120795249939 |
| keywords[3].display_name | Inference |
| keywords[4].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[4].score | 0.5820865035057068 |
| keywords[4].display_name | Convolutional neural network |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.5626733303070068 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[6].score | 0.5484106540679932 |
| keywords[6].display_name | Artificial neural network |
| keywords[7].id | https://openalex.org/keywords/software |
| keywords[7].score | 0.5356582999229431 |
| keywords[7].display_name | Software |
| keywords[8].id | https://openalex.org/keywords/pipeline |
| keywords[8].score | 0.5073661208152771 |
| keywords[8].display_name | Pipeline (software) |
| keywords[9].id | https://openalex.org/keywords/computer-engineering |
| keywords[9].score | 0.45627278089523315 |
| keywords[9].display_name | Computer engineering |
| keywords[10].id | https://openalex.org/keywords/speedup |
| keywords[10].score | 0.4355561435222626 |
| keywords[10].display_name | Speedup |
| keywords[11].id | https://openalex.org/keywords/scripting-language |
| keywords[11].score | 0.4304814338684082 |
| keywords[11].display_name | Scripting language |
| keywords[12].id | https://openalex.org/keywords/graphics-pipeline |
| keywords[12].score | 0.4191593527793884 |
| keywords[12].display_name | Graphics pipeline |
| keywords[13].id | https://openalex.org/keywords/machine-learning |
| keywords[13].score | 0.4104394018650055 |
| keywords[13].display_name | Machine learning |
| keywords[14].id | https://openalex.org/keywords/computer-architecture |
| keywords[14].score | 0.3205186128616333 |
| keywords[14].display_name | Computer architecture |
| keywords[15].id | https://openalex.org/keywords/parallel-computing |
| keywords[15].score | 0.24629586935043335 |
| keywords[15].display_name | Parallel computing |
| keywords[16].id | https://openalex.org/keywords/programming-language |
| keywords[16].score | 0.21547934412956238 |
| keywords[16].display_name | Programming language |
| keywords[17].id | https://openalex.org/keywords/computer-graphics |
| keywords[17].score | 0.21244144439697266 |
| keywords[17].display_name | Computer graphics |
| keywords[18].id | https://openalex.org/keywords/3d-computer-graphics |
| keywords[18].score | 0.16258496046066284 |
| keywords[18].display_name | 3D computer graphics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2209.15427 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2209.15427 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2209.15427 |
| locations[1].id | doi:10.48550/arxiv.2209.15427 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2209.15427 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5025663030 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-9210-3426 |
| authorships[0].author.display_name | Fabian Tschopp |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Tschopp, Fabian |
| authorships[0].is_corresponding | True |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2209.15427 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Tuning of Mixture-of-Experts Mixed-Precision Neural Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10320 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9976000189781189 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/1702 |
| primary_topic.subfield.display_name | Artificial Intelligence |
| primary_topic.display_name | Neural Networks and Applications |
| related_works | https://openalex.org/W3023169329, https://openalex.org/W4389470870, https://openalex.org/W2782165897, https://openalex.org/W1582950852, https://openalex.org/W4300438041, https://openalex.org/W2054104202, https://openalex.org/W2139703748, https://openalex.org/W2761254753, https://openalex.org/W1024825291, https://openalex.org/W2188981919 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2209.15427 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2209.15427 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2209.15427 |
| primary_location.id | pmh:oai:arXiv.org:2209.15427 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2209.15427 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2209.15427 |
| publication_date | 2022-09-29 |
| publication_year | 2022 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 4, 93 |
| abstract_inverted_index.We | 106, 125 |
| abstract_inverted_index.as | 159 |
| abstract_inverted_index.be | 84, 137 |
| abstract_inverted_index.in | 12, 29, 61, 78, 87 |
| abstract_inverted_index.is | 157 |
| abstract_inverted_index.of | 95, 148 |
| abstract_inverted_index.on | 70, 101, 122 |
| abstract_inverted_index.so | 22 |
| abstract_inverted_index.to | 59, 63, 97, 108, 113, 120, 139 |
| abstract_inverted_index.up | 112, 119 |
| abstract_inverted_index.we | 91 |
| abstract_inverted_index.The | 144 |
| abstract_inverted_index.and | 16, 32, 53, 66, 153 |
| abstract_inverted_index.can | 83, 135 |
| abstract_inverted_index.for | 41, 103 |
| abstract_inverted_index.has | 2, 19 |
| abstract_inverted_index.how | 131 |
| abstract_inverted_index.low | 21 |
| abstract_inverted_index.new | 35, 48 |
| abstract_inverted_index.the | 132 |
| abstract_inverted_index.Deep | 0 |
| abstract_inverted_index.Open | 160 |
| abstract_inverted_index.This | 45 |
| abstract_inverted_index.adds | 47 |
| abstract_inverted_index.been | 20 |
| abstract_inverted_index.data | 6, 49 |
| abstract_inverted_index.deep | 26 |
| abstract_inverted_index.far. | 23 |
| abstract_inverted_index.five | 128 |
| abstract_inverted_index.save | 64 |
| abstract_inverted_index.with | 37, 75, 127 |
| abstract_inverted_index.work | 46 |
| abstract_inverted_index.3.01x | 121 |
| abstract_inverted_index.3.29x | 114 |
| abstract_inverted_index.8-bit | 54 |
| abstract_inverted_index.Caffe | 60, 155 |
| abstract_inverted_index.image | 104 |
| abstract_inverted_index.mode. | 89 |
| abstract_inverted_index.order | 62 |
| abstract_inverted_index.speed | 69, 100, 118 |
| abstract_inverted_index.types | 50 |
| abstract_inverted_index.usage | 111 |
| abstract_inverted_index.while | 115 |
| abstract_inverted_index.whole | 145 |
| abstract_inverted_index.16-bit | 52, 56 |
| abstract_inverted_index.Often, | 24 |
| abstract_inverted_index.Source | 161 |
| abstract_inverted_index.adding | 25 |
| abstract_inverted_index.become | 3 |
| abstract_inverted_index.common | 77 |
| abstract_inverted_index.easily | 136 |
| abstract_inverted_index.memory | 65, 110 |
| abstract_inverted_index.models | 82 |
| abstract_inverted_index.neural | 43 |
| abstract_inverted_index.point) | 58 |
| abstract_inverted_index.python | 151 |
| abstract_inverted_index.signal | 38 |
| abstract_inverted_index.simple | 129 |
| abstract_inverted_index.suited | 40 |
| abstract_inverted_index.useful | 5 |
| abstract_inverted_index.AlexNet | 102 |
| abstract_inverted_index.OpenCL, | 76 |
| abstract_inverted_index.applied | 138 |
| abstract_inverted_index.certain | 123 |
| abstract_inverted_index.devices | 18, 33 |
| abstract_inverted_index.example | 150 |
| abstract_inverted_index.however | 9 |
| abstract_inverted_index.machine | 141 |
| abstract_inverted_index.managed | 107 |
| abstract_inverted_index.method, | 8 |
| abstract_inverted_index.models, | 149 |
| abstract_inverted_index.propose | 92 |
| abstract_inverted_index.scripts | 152 |
| abstract_inverted_index.Existing | 81 |
| abstract_inverted_index.adaption | 11 |
| abstract_inverted_index.analysis | 7 |
| abstract_inverted_index.computer | 14 |
| abstract_inverted_index.decrease | 109 |
| abstract_inverted_index.devices. | 80, 124 |
| abstract_inverted_index.embedded | 17 |
| abstract_inverted_index.everyday | 79 |
| abstract_inverted_index.examples | 130 |
| abstract_inverted_index.executed | 85 |
| abstract_inverted_index.existing | 71 |
| abstract_inverted_index.floating | 57 |
| abstract_inverted_index.graphics | 73 |
| abstract_inverted_index.hardware | 36 |
| abstract_inverted_index.increase | 67, 98 |
| abstract_inverted_index.integer, | 55 |
| abstract_inverted_index.learning | 1, 27, 142 |
| abstract_inverted_index.library, | 156 |
| abstract_inverted_index.modified | 154 |
| abstract_inverted_index.requires | 34 |
| abstract_inverted_index.software | 15 |
| abstract_inverted_index.available | 158 |
| abstract_inverted_index.commodity | 72 |
| abstract_inverted_index.different | 140 |
| abstract_inverted_index.inference | 28, 68, 99, 117 |
| abstract_inverted_index.networks. | 44 |
| abstract_inverted_index.pipeline, | 146 |
| abstract_inverted_index.presented | 133 |
| abstract_inverted_index.problems. | 143 |
| abstract_inverted_index.software. | 162 |
| abstract_inverted_index.variation | 94 |
| abstract_inverted_index.(quantized | 51 |
| abstract_inverted_index.consisting | 147 |
| abstract_inverted_index.increasing | 116 |
| abstract_inverted_index.mainstream | 10, 30 |
| abstract_inverted_index.processors | 39, 74 |
| abstract_inverted_index.techniques | 134 |
| abstract_inverted_index.demonstrate | 126 |
| abstract_inverted_index.distributed | 13 |
| abstract_inverted_index.applications | 31 |
| abstract_inverted_index.effortlessly | 86 |
| abstract_inverted_index.Additionally, | 90 |
| abstract_inverted_index.convolutional | 42 |
| abstract_inverted_index.classification. | 105 |
| abstract_inverted_index.mixed-precision | 88 |
| abstract_inverted_index.mixture-of-experts | 96 |
| cited_by_percentile_year | |
| corresponding_author_ids | https://openalex.org/A5025663030 |
| countries_distinct_count | 0 |
| institutions_distinct_count | 1 |
| citation_normalized_percentile |