Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift Article Swipe
Sergey Ioffe
,
Christian Szegedy
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.57702/o9raffed
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.57702/o9raffed
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters.
Related Topics
Concepts
Normalization (sociology)
Initialization
Computer science
Artificial intelligence
Margin (machine learning)
Artificial neural network
Covariate
Training (meteorology)
Deep neural networks
Word error rate
Deep learning
Training set
Machine learning
Pattern recognition (psychology)
Sociology
Meteorology
Anthropology
Programming language
Physics
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://export.arxiv.org/pdf/1502.03167
- OA Status
- green
- Cited By
- 15635
- References
- 16
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W2949117887
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W2949117887Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.57702/o9raffedDigital Object Identifier
- Title
-
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate ShiftWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-01-01Full publication date if available
- Authors
-
Sergey Ioffe, Christian SzegedyList of authors in order
- Landing page
-
https://export.arxiv.org/pdf/1502.03167Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://export.arxiv.org/pdf/1502.03167Direct OA link when available
- Concepts
-
Normalization (sociology), Initialization, Computer science, Artificial intelligence, Margin (machine learning), Artificial neural network, Covariate, Training (meteorology), Deep neural networks, Word error rate, Deep learning, Training set, Machine learning, Pattern recognition (psychology), Sociology, Meteorology, Anthropology, Programming language, PhysicsTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
15635Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 3, 2024: 8, 2023: 20, 2022: 129, 2021: 3260Per-year citation counts (last 5 years)
- References (count)
-
16Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W2949117887 |
|---|---|
| doi | https://doi.org/10.57702/o9raffed |
| ids.doi | https://doi.org/10.57702/o9raffed |
| ids.mag | 2949117887 |
| ids.openalex | https://openalex.org/W2949117887 |
| fwci | |
| type | preprint |
| title | Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11307 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9997000098228455 |
| 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 | Domain Adaptation and Few-Shot Learning |
| topics[1].id | https://openalex.org/T10775 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9986000061035156 |
| 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 | Generative Adversarial Networks and Image Synthesis |
| topics[2].id | https://openalex.org/T10036 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9980000257492065 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1707 |
| topics[2].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[2].display_name | Advanced Neural Network Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C136886441 |
| concepts[0].level | 2 |
| concepts[0].score | 0.932510495185852 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q926129 |
| concepts[0].display_name | Normalization (sociology) |
| concepts[1].id | https://openalex.org/C114466953 |
| concepts[1].level | 2 |
| concepts[1].score | 0.918904185295105 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q6034165 |
| concepts[1].display_name | Initialization |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.7289332151412964 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.5829833149909973 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C774472 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5587779879570007 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q6760393 |
| concepts[4].display_name | Margin (machine learning) |
| concepts[5].id | https://openalex.org/C50644808 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5362868309020996 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[5].display_name | Artificial neural network |
| concepts[6].id | https://openalex.org/C119043178 |
| concepts[6].level | 2 |
| concepts[6].score | 0.5331700444221497 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q320723 |
| concepts[6].display_name | Covariate |
| concepts[7].id | https://openalex.org/C2777211547 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5086577534675598 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q17141490 |
| concepts[7].display_name | Training (meteorology) |
| concepts[8].id | https://openalex.org/C2984842247 |
| concepts[8].level | 3 |
| concepts[8].score | 0.506550669670105 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[8].display_name | Deep neural networks |
| concepts[9].id | https://openalex.org/C40969351 |
| concepts[9].level | 2 |
| concepts[9].score | 0.47505757212638855 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q3516228 |
| concepts[9].display_name | Word error rate |
| concepts[10].id | https://openalex.org/C108583219 |
| concepts[10].level | 2 |
| concepts[10].score | 0.45266589522361755 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[10].display_name | Deep learning |
| concepts[11].id | https://openalex.org/C51632099 |
| concepts[11].level | 2 |
| concepts[11].score | 0.4503152370452881 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q3985153 |
| concepts[11].display_name | Training set |
| concepts[12].id | https://openalex.org/C119857082 |
| concepts[12].level | 1 |
| concepts[12].score | 0.4181462228298187 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[12].display_name | Machine learning |
| concepts[13].id | https://openalex.org/C153180895 |
| concepts[13].level | 2 |
| concepts[13].score | 0.37772560119628906 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[13].display_name | Pattern recognition (psychology) |
| concepts[14].id | https://openalex.org/C144024400 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q21201 |
| concepts[14].display_name | Sociology |
| concepts[15].id | https://openalex.org/C153294291 |
| concepts[15].level | 1 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q25261 |
| concepts[15].display_name | Meteorology |
| concepts[16].id | https://openalex.org/C19165224 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q23404 |
| concepts[16].display_name | Anthropology |
| concepts[17].id | https://openalex.org/C199360897 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[17].display_name | Programming language |
| concepts[18].id | https://openalex.org/C121332964 |
| concepts[18].level | 0 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[18].display_name | Physics |
| keywords[0].id | https://openalex.org/keywords/normalization |
| keywords[0].score | 0.932510495185852 |
| keywords[0].display_name | Normalization (sociology) |
| keywords[1].id | https://openalex.org/keywords/initialization |
| keywords[1].score | 0.918904185295105 |
| keywords[1].display_name | Initialization |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.7289332151412964 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.5829833149909973 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/margin |
| keywords[4].score | 0.5587779879570007 |
| keywords[4].display_name | Margin (machine learning) |
| keywords[5].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[5].score | 0.5362868309020996 |
| keywords[5].display_name | Artificial neural network |
| keywords[6].id | https://openalex.org/keywords/covariate |
| keywords[6].score | 0.5331700444221497 |
| keywords[6].display_name | Covariate |
| keywords[7].id | https://openalex.org/keywords/training |
| keywords[7].score | 0.5086577534675598 |
| keywords[7].display_name | Training (meteorology) |
| keywords[8].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[8].score | 0.506550669670105 |
| keywords[8].display_name | Deep neural networks |
| keywords[9].id | https://openalex.org/keywords/word-error-rate |
| keywords[9].score | 0.47505757212638855 |
| keywords[9].display_name | Word error rate |
| keywords[10].id | https://openalex.org/keywords/deep-learning |
| keywords[10].score | 0.45266589522361755 |
| keywords[10].display_name | Deep learning |
| keywords[11].id | https://openalex.org/keywords/training-set |
| keywords[11].score | 0.4503152370452881 |
| keywords[11].display_name | Training set |
| keywords[12].id | https://openalex.org/keywords/machine-learning |
| keywords[12].score | 0.4181462228298187 |
| keywords[12].display_name | Machine learning |
| keywords[13].id | https://openalex.org/keywords/pattern-recognition |
| keywords[13].score | 0.37772560119628906 |
| keywords[13].display_name | Pattern recognition (psychology) |
| language | en |
| locations[0].id | mag:2949117887 |
| 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 | |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | arXiv (Cornell University) |
| locations[0].landing_page_url | http://export.arxiv.org/pdf/1502.03167 |
| locations[1].id | doi:10.57702/o9raffed |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S7407053387 |
| locations[1].source.type | repository |
| locations[1].source.is_oa | False |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | TIB Data Manager |
| locations[1].source.host_organization | |
| locations[1].source.host_organization_name | |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | dataset |
| 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/10.57702/o9raffed |
| indexed_in | datacite |
| authorships[0].author.id | https://openalex.org/A5032800189 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Sergey Ioffe |
| authorships[0].countries | US |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[0].affiliations[0].raw_affiliation_string | Google, 1600 Amphitheatre Pkwy, Mountain View, CA 94043 |
| authorships[0].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[0].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[0].institutions[0].type | company |
| authorships[0].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[0].institutions[0].country_code | US |
| authorships[0].institutions[0].display_name | Google (United States) |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Sergey Ioffe |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Google, 1600 Amphitheatre Pkwy, Mountain View, CA 94043 |
| authorships[1].author.id | https://openalex.org/A5002183320 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-4295-1851 |
| authorships[1].author.display_name | Christian Szegedy |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I1291425158 |
| authorships[1].affiliations[0].raw_affiliation_string | Google, 1600 Amphitheatre Pkwy, Mountain View, CA 94043 |
| authorships[1].institutions[0].id | https://openalex.org/I1291425158 |
| authorships[1].institutions[0].ror | https://ror.org/00njsd438 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I1291425158, https://openalex.org/I4210128969 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Google (United States) |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Christian Szegedy |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Google, 1600 Amphitheatre Pkwy, Mountain View, CA 94043 |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | http://export.arxiv.org/pdf/1502.03167 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11307 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9997000098228455 |
| 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 | Domain Adaptation and Few-Shot Learning |
| related_works | https://openalex.org/W3118608800, https://openalex.org/W2964121744, https://openalex.org/W2963446712, https://openalex.org/W2919115771, https://openalex.org/W2194775991, https://openalex.org/W2183341477, https://openalex.org/W2163605009, https://openalex.org/W2117539524, https://openalex.org/W2112796928, https://openalex.org/W2108598243, https://openalex.org/W2099471712, https://openalex.org/W2097117768, https://openalex.org/W2095705004, https://openalex.org/W2064675550, https://openalex.org/W1903029394, https://openalex.org/W1901129140, https://openalex.org/W1686810756, https://openalex.org/W1677182931, https://openalex.org/W1665214252, https://openalex.org/W1533861849 |
| cited_by_count | 15635 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 3 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 8 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 20 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 129 |
| counts_by_year[4].year | 2021 |
| counts_by_year[4].cited_by_count | 3260 |
| counts_by_year[5].year | 2020 |
| counts_by_year[5].cited_by_count | 3906 |
| counts_by_year[6].year | 2019 |
| counts_by_year[6].cited_by_count | 3538 |
| counts_by_year[7].year | 2018 |
| counts_by_year[7].cited_by_count | 2482 |
| counts_by_year[8].year | 2017 |
| counts_by_year[8].cited_by_count | 1547 |
| counts_by_year[9].year | 2016 |
| counts_by_year[9].cited_by_count | 607 |
| counts_by_year[10].year | 2015 |
| counts_by_year[10].cited_by_count | 128 |
| counts_by_year[11].year | 2014 |
| counts_by_year[11].cited_by_count | 7 |
| locations_count | 2 |
| best_oa_location.id | mag:2949117887 |
| 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 | |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | arXiv (Cornell University) |
| best_oa_location.landing_page_url | http://export.arxiv.org/pdf/1502.03167 |
| primary_location.id | mag:2949117887 |
| 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 | |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | arXiv (Cornell University) |
| primary_location.landing_page_url | http://export.arxiv.org/pdf/1502.03167 |
| publication_date | 2024-01-01 |
| publication_year | 2024 |
| referenced_works | https://openalex.org/W2127230474, https://openalex.org/W104184427, https://openalex.org/W2019866374, https://openalex.org/W2084894614, https://openalex.org/W2123649031, https://openalex.org/W2152424459, https://openalex.org/W2168231600, https://openalex.org/W2146502635, https://openalex.org/W2952020226, https://openalex.org/W2034368206, https://openalex.org/W1762484328, https://openalex.org/W2125930537, https://openalex.org/W2095705004, https://openalex.org/W2950179405, https://openalex.org/W1677182931, https://openalex.org/W2112796928 |
| referenced_works_count | 16 |
| abstract_inverted_index.a | 77, 111, 123, 146 |
| abstract_inverted_index.14 | 135 |
| abstract_inverted_index.It | 107 |
| abstract_inverted_index.We | 52 |
| abstract_inverted_index.an | 150 |
| abstract_inverted_index.as | 19, 57, 110 |
| abstract_inverted_index.be | 102 |
| abstract_inverted_index.by | 6, 32, 65, 145 |
| abstract_inverted_index.in | 113 |
| abstract_inverted_index.is | 4 |
| abstract_inverted_index.it | 43 |
| abstract_inverted_index.of | 12, 22, 79, 152, 177 |
| abstract_inverted_index.on | 162 |
| abstract_inverted_index.to | 46, 54, 95, 122 |
| abstract_inverted_index.us | 94 |
| abstract_inverted_index.we | 155 |
| abstract_inverted_index.Our | 69 |
| abstract_inverted_index.and | 37, 41, 61, 83, 101, 140 |
| abstract_inverted_index.for | 87, 119 |
| abstract_inverted_index.its | 72 |
| abstract_inverted_index.the | 7, 10, 20, 23, 30, 63, 80, 85, 117, 131, 142, 158, 175 |
| abstract_inverted_index.use | 96 |
| abstract_inverted_index.(and | 170 |
| abstract_inverted_index.4.8% | 171 |
| abstract_inverted_index.4.9% | 166 |
| abstract_inverted_index.Deep | 1 |
| abstract_inverted_index.This | 27 |
| abstract_inverted_index.acts | 109 |
| abstract_inverted_index.also | 108 |
| abstract_inverted_index.best | 159 |
| abstract_inverted_index.down | 29 |
| abstract_inverted_index.each | 13, 88 |
| abstract_inverted_index.fact | 8 |
| abstract_inverted_index.from | 74 |
| abstract_inverted_index.hard | 45 |
| abstract_inverted_index.less | 103 |
| abstract_inverted_index.much | 97 |
| abstract_inverted_index.need | 118 |
| abstract_inverted_index.part | 78 |
| abstract_inverted_index.same | 132 |
| abstract_inverted_index.some | 114 |
| abstract_inverted_index.test | 172 |
| abstract_inverted_index.that | 9 |
| abstract_inverted_index.this | 55 |
| abstract_inverted_index.upon | 157 |
| abstract_inverted_index.with | 49, 134 |
| abstract_inverted_index.Batch | 91, 128 |
| abstract_inverted_index.Using | 149 |
| abstract_inverted_index.about | 105 |
| abstract_inverted_index.beats | 141 |
| abstract_inverted_index.cases | 115 |
| abstract_inverted_index.draws | 71 |
| abstract_inverted_index.error | 169 |
| abstract_inverted_index.fewer | 137 |
| abstract_inverted_index.human | 178 |
| abstract_inverted_index.image | 125 |
| abstract_inverted_index.layer | 67 |
| abstract_inverted_index.lower | 34 |
| abstract_inverted_index.makes | 42 |
| abstract_inverted_index.model | 81, 144 |
| abstract_inverted_index.rates | 36, 100 |
| abstract_inverted_index.refer | 53 |
| abstract_inverted_index.slows | 28 |
| abstract_inverted_index.times | 136 |
| abstract_inverted_index.top-5 | 167 |
| abstract_inverted_index.train | 47 |
| abstract_inverted_index.Neural | 2 |
| abstract_inverted_index.allows | 93 |
| abstract_inverted_index.during | 17 |
| abstract_inverted_index.higher | 98 |
| abstract_inverted_index.inputs | 15 |
| abstract_inverted_index.layers | 25 |
| abstract_inverted_index.making | 75 |
| abstract_inverted_index.method | 70 |
| abstract_inverted_index.model, | 127 |
| abstract_inverted_index.models | 48 |
| abstract_inverted_index.result | 161 |
| abstract_inverted_index.shift, | 60 |
| abstract_inverted_index.steps, | 139 |
| abstract_inverted_index.Applied | 121 |
| abstract_inverted_index.address | 62 |
| abstract_inverted_index.careful | 38, 104 |
| abstract_inverted_index.change. | 26 |
| abstract_inverted_index.changes | 16 |
| abstract_inverted_index.error), | 173 |
| abstract_inverted_index.improve | 156 |
| abstract_inverted_index.inputs. | 68 |
| abstract_inverted_index.layer's | 14 |
| abstract_inverted_index.margin. | 148 |
| abstract_inverted_index.problem | 64 |
| abstract_inverted_index.raters. | 179 |
| abstract_inverted_index.Dropout. | 120 |
| abstract_inverted_index.ImageNet | 163 |
| abstract_inverted_index.Networks | 3 |
| abstract_inverted_index.Training | 0 |
| abstract_inverted_index.accuracy | 133, 176 |
| abstract_inverted_index.achieves | 130 |
| abstract_inverted_index.ensemble | 151 |
| abstract_inverted_index.internal | 58 |
| abstract_inverted_index.learning | 35, 99 |
| abstract_inverted_index.original | 143 |
| abstract_inverted_index.previous | 24 |
| abstract_inverted_index.reaching | 165 |
| abstract_inverted_index.strength | 73 |
| abstract_inverted_index.training | 31, 89, 138 |
| abstract_inverted_index.covariate | 59 |
| abstract_inverted_index.exceeding | 174 |
| abstract_inverted_index.networks, | 154 |
| abstract_inverted_index.parameter | 39 |
| abstract_inverted_index.published | 160 |
| abstract_inverted_index.requiring | 33 |
| abstract_inverted_index.training, | 18 |
| abstract_inverted_index.parameters | 21 |
| abstract_inverted_index.performing | 84 |
| abstract_inverted_index.phenomenon | 56 |
| abstract_inverted_index.saturating | 50 |
| abstract_inverted_index.validation | 168 |
| abstract_inverted_index.complicated | 5 |
| abstract_inverted_index.eliminating | 116 |
| abstract_inverted_index.mini-batch. | 90 |
| abstract_inverted_index.normalizing | 66 |
| abstract_inverted_index.notoriously | 44 |
| abstract_inverted_index.significant | 147 |
| abstract_inverted_index.architecture | 82 |
| abstract_inverted_index.distribution | 11 |
| abstract_inverted_index.regularizer, | 112 |
| abstract_inverted_index.Normalization | 92, 129 |
| abstract_inverted_index.normalization | 76, 86 |
| abstract_inverted_index.classification | 126 |
| abstract_inverted_index.classification: | 164 |
| abstract_inverted_index.initialization, | 40 |
| abstract_inverted_index.initialization. | 106 |
| abstract_inverted_index.nonlinearities. | 51 |
| abstract_inverted_index.batch-normalized | 153 |
| abstract_inverted_index.state-of-the-art | 124 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 2 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/4 |
| sustainable_development_goals[0].score | 0.699999988079071 |
| sustainable_development_goals[0].display_name | Quality Education |
| citation_normalized_percentile |