Mutual Information of Neural Network Initialisations: Mean Field Approximations Article Swipe
Jared Tanner
,
Giuseppe Ughi
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.1109/isit45174.2021.9518278
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.1109/isit45174.2021.9518278
The ability to train randomly initialised deep neural networks is known to depend strongly on the variance of the weight matrices and biases as well as the choice of nonlinear activation. Here we complement the existing geometric analysis of this phenomenon with an information theoretic alternative. Lower bounds are derived for the mutual information between an input and hidden layer outputs. Using a mean field analysis we are able to provide analytic lower bounds as functions of network weight and bias variances as well as the choice of nonlinear activation. These results show that initialisations known to be optimal from a training point of view are also superior from a mutual information perspective.
Related Topics
Concepts
Mutual information
Complement (music)
Artificial neural network
Perspective (graphical)
Nonlinear system
Computer science
Point (geometry)
Variance (accounting)
Field (mathematics)
Mathematics
Artificial intelligence
Applied mathematics
Pure mathematics
Physics
Chemistry
Phenotype
Quantum mechanics
Geometry
Complementation
Business
Accounting
Biochemistry
Gene
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- https://doi.org/10.1109/isit45174.2021.9518278
- OA Status
- green
- References
- 19
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W3126823575
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3126823575Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/isit45174.2021.9518278Digital Object Identifier
- Title
-
Mutual Information of Neural Network Initialisations: Mean Field ApproximationsWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-07-12Full publication date if available
- Authors
-
Jared Tanner, Giuseppe UghiList of authors in order
- Landing page
-
https://doi.org/10.1109/isit45174.2021.9518278Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2102.04374Direct OA link when available
- Concepts
-
Mutual information, Complement (music), Artificial neural network, Perspective (graphical), Nonlinear system, Computer science, Point (geometry), Variance (accounting), Field (mathematics), Mathematics, Artificial intelligence, Applied mathematics, Pure mathematics, Physics, Chemistry, Phenotype, Quantum mechanics, Geometry, Complementation, Business, Accounting, Biochemistry, GeneTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- References (count)
-
19Number of works referenced by this work
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W3126823575 |
|---|---|
| doi | https://doi.org/10.1109/isit45174.2021.9518278 |
| ids.doi | https://doi.org/10.1109/isit45174.2021.9518278 |
| ids.mag | 3126823575 |
| ids.openalex | https://openalex.org/W3126823575 |
| fwci | 0.0 |
| type | preprint |
| title | Mutual Information of Neural Network Initialisations: Mean Field Approximations |
| biblio.issue | |
| biblio.volume | 3 |
| biblio.last_page | 818 |
| biblio.first_page | 813 |
| 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 | 0.9994999766349792 |
| 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/T12261 |
| topics[1].field.id | https://openalex.org/fields/31 |
| topics[1].field.display_name | Physics and Astronomy |
| topics[1].score | 0.996999979019165 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/3109 |
| topics[1].subfield.display_name | Statistical and Nonlinear Physics |
| topics[1].display_name | Statistical Mechanics and Entropy |
| topics[2].id | https://openalex.org/T12676 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9968000054359436 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Machine Learning and ELM |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C152139883 |
| concepts[0].level | 2 |
| concepts[0].score | 0.7895584106445312 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q252973 |
| concepts[0].display_name | Mutual information |
| concepts[1].id | https://openalex.org/C112313634 |
| concepts[1].level | 5 |
| concepts[1].score | 0.7566794157028198 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q7886648 |
| concepts[1].display_name | Complement (music) |
| concepts[2].id | https://openalex.org/C50644808 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6353236436843872 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[2].display_name | Artificial neural network |
| concepts[3].id | https://openalex.org/C12713177 |
| concepts[3].level | 2 |
| concepts[3].score | 0.5884007215499878 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q1900281 |
| concepts[3].display_name | Perspective (graphical) |
| concepts[4].id | https://openalex.org/C158622935 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5837039947509766 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q660848 |
| concepts[4].display_name | Nonlinear system |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.49904561042785645 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C28719098 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4922129213809967 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q44946 |
| concepts[6].display_name | Point (geometry) |
| concepts[7].id | https://openalex.org/C196083921 |
| concepts[7].level | 2 |
| concepts[7].score | 0.48330116271972656 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7915758 |
| concepts[7].display_name | Variance (accounting) |
| concepts[8].id | https://openalex.org/C9652623 |
| concepts[8].level | 2 |
| concepts[8].score | 0.48280465602874756 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q190109 |
| concepts[8].display_name | Field (mathematics) |
| concepts[9].id | https://openalex.org/C33923547 |
| concepts[9].level | 0 |
| concepts[9].score | 0.4709392786026001 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[9].display_name | Mathematics |
| concepts[10].id | https://openalex.org/C154945302 |
| concepts[10].level | 1 |
| concepts[10].score | 0.36543214321136475 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[10].display_name | Artificial intelligence |
| concepts[11].id | https://openalex.org/C28826006 |
| concepts[11].level | 1 |
| concepts[11].score | 0.35219132900238037 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q33521 |
| concepts[11].display_name | Applied mathematics |
| concepts[12].id | https://openalex.org/C202444582 |
| concepts[12].level | 1 |
| concepts[12].score | 0.12777596712112427 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q837863 |
| concepts[12].display_name | Pure mathematics |
| concepts[13].id | https://openalex.org/C121332964 |
| concepts[13].level | 0 |
| concepts[13].score | 0.07761189341545105 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[13].display_name | Physics |
| concepts[14].id | https://openalex.org/C185592680 |
| concepts[14].level | 0 |
| concepts[14].score | 0.0 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[14].display_name | Chemistry |
| concepts[15].id | https://openalex.org/C127716648 |
| concepts[15].level | 3 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q104053 |
| concepts[15].display_name | Phenotype |
| concepts[16].id | https://openalex.org/C62520636 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[16].display_name | Quantum mechanics |
| concepts[17].id | https://openalex.org/C2524010 |
| concepts[17].level | 1 |
| concepts[17].score | 0.0 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[17].display_name | Geometry |
| concepts[18].id | https://openalex.org/C188082640 |
| concepts[18].level | 4 |
| concepts[18].score | 0.0 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q1780899 |
| concepts[18].display_name | Complementation |
| concepts[19].id | https://openalex.org/C144133560 |
| concepts[19].level | 0 |
| concepts[19].score | 0.0 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q4830453 |
| concepts[19].display_name | Business |
| concepts[20].id | https://openalex.org/C121955636 |
| concepts[20].level | 1 |
| concepts[20].score | 0.0 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q4116214 |
| concepts[20].display_name | Accounting |
| concepts[21].id | https://openalex.org/C55493867 |
| concepts[21].level | 1 |
| concepts[21].score | 0.0 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[21].display_name | Biochemistry |
| concepts[22].id | https://openalex.org/C104317684 |
| concepts[22].level | 2 |
| concepts[22].score | 0.0 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[22].display_name | Gene |
| keywords[0].id | https://openalex.org/keywords/mutual-information |
| keywords[0].score | 0.7895584106445312 |
| keywords[0].display_name | Mutual information |
| keywords[1].id | https://openalex.org/keywords/complement |
| keywords[1].score | 0.7566794157028198 |
| keywords[1].display_name | Complement (music) |
| keywords[2].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[2].score | 0.6353236436843872 |
| keywords[2].display_name | Artificial neural network |
| keywords[3].id | https://openalex.org/keywords/perspective |
| keywords[3].score | 0.5884007215499878 |
| keywords[3].display_name | Perspective (graphical) |
| keywords[4].id | https://openalex.org/keywords/nonlinear-system |
| keywords[4].score | 0.5837039947509766 |
| keywords[4].display_name | Nonlinear system |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.49904561042785645 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/point |
| keywords[6].score | 0.4922129213809967 |
| keywords[6].display_name | Point (geometry) |
| keywords[7].id | https://openalex.org/keywords/variance |
| keywords[7].score | 0.48330116271972656 |
| keywords[7].display_name | Variance (accounting) |
| keywords[8].id | https://openalex.org/keywords/field |
| keywords[8].score | 0.48280465602874756 |
| keywords[8].display_name | Field (mathematics) |
| keywords[9].id | https://openalex.org/keywords/mathematics |
| keywords[9].score | 0.4709392786026001 |
| keywords[9].display_name | Mathematics |
| keywords[10].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[10].score | 0.36543214321136475 |
| keywords[10].display_name | Artificial intelligence |
| keywords[11].id | https://openalex.org/keywords/applied-mathematics |
| keywords[11].score | 0.35219132900238037 |
| keywords[11].display_name | Applied mathematics |
| keywords[12].id | https://openalex.org/keywords/pure-mathematics |
| keywords[12].score | 0.12777596712112427 |
| keywords[12].display_name | Pure mathematics |
| keywords[13].id | https://openalex.org/keywords/physics |
| keywords[13].score | 0.07761189341545105 |
| keywords[13].display_name | Physics |
| language | en |
| locations[0].id | doi:10.1109/isit45174.2021.9518278 |
| locations[0].is_oa | False |
| locations[0].source | |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | proceedings-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | 2021 IEEE International Symposium on Information Theory (ISIT) |
| locations[0].landing_page_url | https://doi.org/10.1109/isit45174.2021.9518278 |
| locations[1].id | pmh:oai:arXiv.org:2102.04374 |
| 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 | https://arxiv.org/pdf/2102.04374 |
| locations[1].version | submittedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | False |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | http://arxiv.org/abs/2102.04374 |
| locations[2].id | mag:3126823575 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4306400194 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | True |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | arXiv (Cornell University) |
| locations[2].source.host_organization | https://openalex.org/I205783295 |
| locations[2].source.host_organization_name | Cornell University |
| locations[2].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[2].license | |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | |
| locations[2].license_id | |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | arXiv (Cornell University) |
| locations[2].landing_page_url | https://arxiv.org/pdf/2102.04374 |
| locations[3].id | doi:10.48550/arxiv.2102.04374 |
| locations[3].is_oa | True |
| locations[3].source.id | https://openalex.org/S4306400194 |
| locations[3].source.issn | |
| locations[3].source.type | repository |
| locations[3].source.is_oa | True |
| locations[3].source.issn_l | |
| locations[3].source.is_core | False |
| locations[3].source.is_in_doaj | False |
| locations[3].source.display_name | arXiv (Cornell University) |
| locations[3].source.host_organization | https://openalex.org/I205783295 |
| locations[3].source.host_organization_name | Cornell University |
| locations[3].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[3].license | |
| locations[3].pdf_url | |
| locations[3].version | |
| locations[3].raw_type | article |
| locations[3].license_id | |
| locations[3].is_accepted | False |
| locations[3].is_published | |
| locations[3].raw_source_name | |
| locations[3].landing_page_url | https://doi.org/10.48550/arxiv.2102.04374 |
| indexed_in | arxiv, crossref, datacite |
| authorships[0].author.id | https://openalex.org/A5059562923 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-5561-9949 |
| authorships[0].author.display_name | Jared Tanner |
| authorships[0].countries | GB |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I40120149 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Oxford,Mathematical Institute,Oxford,UK,OX2 6GG |
| authorships[0].institutions[0].id | https://openalex.org/I40120149 |
| authorships[0].institutions[0].ror | https://ror.org/052gg0110 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I40120149 |
| authorships[0].institutions[0].country_code | GB |
| authorships[0].institutions[0].display_name | University of Oxford |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Jared Tanner |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of Oxford,Mathematical Institute,Oxford,UK,OX2 6GG |
| authorships[1].author.id | https://openalex.org/A5041582928 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Giuseppe Ughi |
| authorships[1].countries | GB |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I40120149 |
| authorships[1].affiliations[0].raw_affiliation_string | University of Oxford. |
| authorships[1].institutions[0].id | https://openalex.org/I40120149 |
| authorships[1].institutions[0].ror | https://ror.org/052gg0110 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I40120149 |
| authorships[1].institutions[0].country_code | GB |
| authorships[1].institutions[0].display_name | University of Oxford |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Giuseppe Ughi |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | University of Oxford. |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2102.04374 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Mutual Information of Neural Network Initialisations: Mean Field Approximations |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| 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 | 0.9994999766349792 |
| 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/W2920676536, https://openalex.org/W3090062522, https://openalex.org/W2970375336, https://openalex.org/W2229184994, https://openalex.org/W2770888898, https://openalex.org/W2118543192, https://openalex.org/W2766635461, https://openalex.org/W2533499697, https://openalex.org/W3195656583, https://openalex.org/W2127538960, https://openalex.org/W2912457996, https://openalex.org/W101457924, https://openalex.org/W2941256613, https://openalex.org/W2963161247, https://openalex.org/W2290456206, https://openalex.org/W3181674477, https://openalex.org/W2065465845, https://openalex.org/W2889819949, https://openalex.org/W2575128619, https://openalex.org/W3006073215 |
| cited_by_count | 0 |
| locations_count | 4 |
| best_oa_location.id | pmh:oai:arXiv.org:2102.04374 |
| 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/2102.04374 |
| 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 | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2102.04374 |
| primary_location.id | doi:10.1109/isit45174.2021.9518278 |
| primary_location.is_oa | False |
| primary_location.source | |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | proceedings-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | 2021 IEEE International Symposium on Information Theory (ISIT) |
| primary_location.landing_page_url | https://doi.org/10.1109/isit45174.2021.9518278 |
| publication_date | 2021-07-12 |
| publication_year | 2021 |
| referenced_works | https://openalex.org/W6639736602, https://openalex.org/W6756362675, https://openalex.org/W2962779416, https://openalex.org/W2922126188, https://openalex.org/W2122925692, https://openalex.org/W6749180595, https://openalex.org/W6754984521, https://openalex.org/W2803439868, https://openalex.org/W2996320484, https://openalex.org/W6717556742, https://openalex.org/W6730172645, https://openalex.org/W1485732691, https://openalex.org/W2593634001, https://openalex.org/W2964041897, https://openalex.org/W2964003773, https://openalex.org/W2962804662, https://openalex.org/W3035096847, https://openalex.org/W2962807446, https://openalex.org/W2964088238 |
| referenced_works_count | 19 |
| abstract_inverted_index.a | 62, 100, 109 |
| abstract_inverted_index.an | 42, 55 |
| abstract_inverted_index.as | 23, 25, 74, 82, 84 |
| abstract_inverted_index.be | 97 |
| abstract_inverted_index.is | 9 |
| abstract_inverted_index.of | 17, 28, 38, 76, 87, 103 |
| abstract_inverted_index.on | 14 |
| abstract_inverted_index.to | 2, 11, 69, 96 |
| abstract_inverted_index.we | 32, 66 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 21, 57, 79 |
| abstract_inverted_index.are | 48, 67, 105 |
| abstract_inverted_index.for | 50 |
| abstract_inverted_index.the | 15, 18, 26, 34, 51, 85 |
| abstract_inverted_index.Here | 31 |
| abstract_inverted_index.able | 68 |
| abstract_inverted_index.also | 106 |
| abstract_inverted_index.bias | 80 |
| abstract_inverted_index.deep | 6 |
| abstract_inverted_index.from | 99, 108 |
| abstract_inverted_index.mean | 63 |
| abstract_inverted_index.show | 92 |
| abstract_inverted_index.that | 93 |
| abstract_inverted_index.this | 39 |
| abstract_inverted_index.view | 104 |
| abstract_inverted_index.well | 24, 83 |
| abstract_inverted_index.with | 41 |
| abstract_inverted_index.Lower | 46 |
| abstract_inverted_index.These | 90 |
| abstract_inverted_index.Using | 61 |
| abstract_inverted_index.field | 64 |
| abstract_inverted_index.input | 56 |
| abstract_inverted_index.known | 10, 95 |
| abstract_inverted_index.layer | 59 |
| abstract_inverted_index.lower | 72 |
| abstract_inverted_index.point | 102 |
| abstract_inverted_index.train | 3 |
| abstract_inverted_index.biases | 22 |
| abstract_inverted_index.bounds | 47, 73 |
| abstract_inverted_index.choice | 27, 86 |
| abstract_inverted_index.depend | 12 |
| abstract_inverted_index.hidden | 58 |
| abstract_inverted_index.mutual | 52, 110 |
| abstract_inverted_index.neural | 7 |
| abstract_inverted_index.weight | 19, 78 |
| abstract_inverted_index.ability | 1 |
| abstract_inverted_index.between | 54 |
| abstract_inverted_index.derived | 49 |
| abstract_inverted_index.network | 77 |
| abstract_inverted_index.optimal | 98 |
| abstract_inverted_index.provide | 70 |
| abstract_inverted_index.results | 91 |
| abstract_inverted_index.analysis | 37, 65 |
| abstract_inverted_index.analytic | 71 |
| abstract_inverted_index.existing | 35 |
| abstract_inverted_index.matrices | 20 |
| abstract_inverted_index.networks | 8 |
| abstract_inverted_index.outputs. | 60 |
| abstract_inverted_index.randomly | 4 |
| abstract_inverted_index.strongly | 13 |
| abstract_inverted_index.superior | 107 |
| abstract_inverted_index.training | 101 |
| abstract_inverted_index.variance | 16 |
| abstract_inverted_index.functions | 75 |
| abstract_inverted_index.geometric | 36 |
| abstract_inverted_index.nonlinear | 29, 88 |
| abstract_inverted_index.theoretic | 44 |
| abstract_inverted_index.variances | 81 |
| abstract_inverted_index.complement | 33 |
| abstract_inverted_index.phenomenon | 40 |
| abstract_inverted_index.activation. | 30, 89 |
| abstract_inverted_index.information | 43, 53, 111 |
| abstract_inverted_index.initialised | 5 |
| abstract_inverted_index.alternative. | 45 |
| abstract_inverted_index.perspective. | 112 |
| abstract_inverted_index.initialisations | 94 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 2 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.41999998688697815 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile.value | 0.01891274 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |