PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions Article Swipe
Eleonora Grassucci
,
Aston Zhang
,
Danilo Comminiello
·
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1109/tnnls.2022.3226772
YOU?
·
· 2022
· Open Access
·
· DOI: https://doi.org/10.1109/tnnls.2022.3226772
Hypercomplex neural networks have proven to reduce the overall number of parameters while ensuring valuable performance by leveraging the properties of Clifford algebras. Recently, hypercomplex linear layers have been further improved by involving efficient parameterized Kronecker products. In this article, we define the parameterization of hypercomplex convolutional layers and introduce the family of parameterized hypercomplex neural networks (PHNNs) that are lightweight and efficient large-scale models. Our method grasps the convolution rules and the filter organization directly from data without requiring a rigidly predefined domain structure to follow. PHNNs are flexible to operate in any user-defined or tuned domain, from 1-D to [Formula: see text] regardless of whether the algebra rules are preset. Such a malleability allows processing multidimensional inputs in their natural domain without annexing further dimensions, as done, instead, in quaternion neural networks (QNNs) for 3-D inputs like color images. As a result, the proposed family of PHNNs operates with 1/n free parameters as regards its analog in the real domain. We demonstrate the versatility of this approach to multiple domains of application by performing experiments on various image datasets and audio datasets in which our method outperforms real and quaternion-valued counterparts. Full code is available at: https://github.com/eleGAN23/HyperNets.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1109/tnnls.2022.3226772
- https://ieeexplore.ieee.org/ielx7/5962385/6104215/09983846.pdf
- OA Status
- hybrid
- Cited By
- 34
- References
- 62
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4312984359
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4312984359Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1109/tnnls.2022.3226772Digital Object Identifier
- Title
-
PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex ConvolutionsWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2022Year of publication
- Publication date
-
2022-12-13Full publication date if available
- Authors
-
Eleonora Grassucci, Aston Zhang, Danilo ComminielloList of authors in order
- Landing page
-
https://doi.org/10.1109/tnnls.2022.3226772Publisher landing page
- PDF URL
-
https://ieeexplore.ieee.org/ielx7/5962385/6104215/09983846.pdfDirect link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
hybridOpen access status per OpenAlex
- OA URL
-
https://ieeexplore.ieee.org/ielx7/5962385/6104215/09983846.pdfDirect OA link when available
- Concepts
-
Hypercomplex number, Parameterized complexity, Artificial neural network, Computer science, Mathematics, Artificial intelligence, Algorithm, Geometry, QuaternionTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
34Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 5, 2024: 16, 2023: 10, 2022: 3Per-year citation counts (last 5 years)
- References (count)
-
62Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4312984359 |
|---|---|
| doi | https://doi.org/10.1109/tnnls.2022.3226772 |
| ids.doi | https://doi.org/10.1109/tnnls.2022.3226772 |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/37015366 |
| ids.openalex | https://openalex.org/W4312984359 |
| fwci | 6.65715989 |
| type | article |
| title | PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions |
| awards[0].id | https://openalex.org/G6207027699 |
| awards[0].funder_id | https://openalex.org/F4320322510 |
| awards[0].display_name | |
| awards[0].funder_award_id | RG11916B88E1942F |
| awards[0].funder_display_name | Sapienza Università di Roma |
| biblio.issue | 6 |
| biblio.volume | 35 |
| biblio.last_page | 8305 |
| biblio.first_page | 8293 |
| 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 | 0.9997000098228455 |
| 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 | Neural Networks and Applications |
| topics[1].id | https://openalex.org/T11447 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9994999766349792 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1711 |
| topics[1].subfield.display_name | Signal Processing |
| topics[1].display_name | Blind Source Separation Techniques |
| topics[2].id | https://openalex.org/T12611 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9965000152587891 |
| 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 | Neural Networks and Reservoir Computing |
| funders[0].id | https://openalex.org/F4320322510 |
| funders[0].ror | https://ror.org/02be6w209 |
| funders[0].display_name | Sapienza Università di Roma |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C203249530 |
| concepts[0].level | 3 |
| concepts[0].score | 0.938147783279419 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q837414 |
| concepts[0].display_name | Hypercomplex number |
| concepts[1].id | https://openalex.org/C165464430 |
| concepts[1].level | 2 |
| concepts[1].score | 0.8726252317428589 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1570441 |
| concepts[1].display_name | Parameterized complexity |
| concepts[2].id | https://openalex.org/C50644808 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5920885801315308 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[2].display_name | Artificial neural network |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.5318624377250671 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C33923547 |
| concepts[4].level | 0 |
| concepts[4].score | 0.4475194811820984 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[4].display_name | Mathematics |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.37636905908584595 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C11413529 |
| concepts[6].level | 1 |
| concepts[6].score | 0.3241835832595825 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[6].display_name | Algorithm |
| concepts[7].id | https://openalex.org/C2524010 |
| concepts[7].level | 1 |
| concepts[7].score | 0.054070353507995605 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[7].display_name | Geometry |
| concepts[8].id | https://openalex.org/C200127275 |
| concepts[8].level | 2 |
| concepts[8].score | 0.049979716539382935 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q173853 |
| concepts[8].display_name | Quaternion |
| keywords[0].id | https://openalex.org/keywords/hypercomplex-number |
| keywords[0].score | 0.938147783279419 |
| keywords[0].display_name | Hypercomplex number |
| keywords[1].id | https://openalex.org/keywords/parameterized-complexity |
| keywords[1].score | 0.8726252317428589 |
| keywords[1].display_name | Parameterized complexity |
| keywords[2].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[2].score | 0.5920885801315308 |
| keywords[2].display_name | Artificial neural network |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.5318624377250671 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/mathematics |
| keywords[4].score | 0.4475194811820984 |
| keywords[4].display_name | Mathematics |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.37636905908584595 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/algorithm |
| keywords[6].score | 0.3241835832595825 |
| keywords[6].display_name | Algorithm |
| keywords[7].id | https://openalex.org/keywords/geometry |
| keywords[7].score | 0.054070353507995605 |
| keywords[7].display_name | Geometry |
| keywords[8].id | https://openalex.org/keywords/quaternion |
| keywords[8].score | 0.049979716539382935 |
| keywords[8].display_name | Quaternion |
| language | en |
| locations[0].id | doi:10.1109/tnnls.2022.3226772 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4210175523 |
| locations[0].source.issn | 2162-237X, 2162-2388 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | False |
| locations[0].source.issn_l | 2162-237X |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | IEEE Transactions on Neural Networks and Learning Systems |
| locations[0].source.host_organization | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_name | Institute of Electrical and Electronics Engineers |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310319808 |
| locations[0].source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| locations[0].license | cc-by |
| locations[0].pdf_url | https://ieeexplore.ieee.org/ielx7/5962385/6104215/09983846.pdf |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | IEEE Transactions on Neural Networks and Learning Systems |
| locations[0].landing_page_url | https://doi.org/10.1109/tnnls.2022.3226772 |
| locations[1].id | pmid:37015366 |
| locations[1].is_oa | False |
| locations[1].source.id | https://openalex.org/S4306525036 |
| locations[1].source.issn | |
| 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 | PubMed |
| locations[1].source.host_organization | https://openalex.org/I1299303238 |
| locations[1].source.host_organization_name | National Institutes of Health |
| locations[1].source.host_organization_lineage | https://openalex.org/I1299303238 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | publishedVersion |
| locations[1].raw_type | |
| locations[1].license_id | |
| locations[1].is_accepted | True |
| locations[1].is_published | True |
| locations[1].raw_source_name | IEEE transactions on neural networks and learning systems |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/37015366 |
| locations[2].id | pmh:oai:iris.uniroma1.it:11573/1665641 |
| locations[2].is_oa | True |
| locations[2].source.id | https://openalex.org/S4377196107 |
| locations[2].source.issn | |
| locations[2].source.type | repository |
| locations[2].source.is_oa | False |
| locations[2].source.issn_l | |
| locations[2].source.is_core | False |
| locations[2].source.is_in_doaj | False |
| locations[2].source.display_name | IRIS Research product catalog (Sapienza University of Rome) |
| locations[2].source.host_organization | |
| locations[2].source.host_organization_name | |
| locations[2].license | cc-by |
| locations[2].pdf_url | |
| locations[2].version | submittedVersion |
| locations[2].raw_type | info:eu-repo/semantics/article |
| locations[2].license_id | https://openalex.org/licenses/cc-by |
| locations[2].is_accepted | False |
| locations[2].is_published | False |
| locations[2].raw_source_name | |
| locations[2].landing_page_url | https://hdl.handle.net/11573/1665641 |
| indexed_in | crossref, pubmed |
| authorships[0].author.id | https://openalex.org/A5003606065 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-4626-4506 |
| authorships[0].author.display_name | Eleonora Grassucci |
| authorships[0].countries | IT |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I861853513 |
| authorships[0].affiliations[0].raw_affiliation_string | Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Roma, Italy |
| authorships[0].institutions[0].id | https://openalex.org/I861853513 |
| authorships[0].institutions[0].ror | https://ror.org/02be6w209 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I861853513 |
| authorships[0].institutions[0].country_code | IT |
| authorships[0].institutions[0].display_name | Sapienza University of Rome |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Eleonora Grassucci |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Roma, Italy |
| authorships[1].author.id | https://openalex.org/A5049841140 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Aston Zhang |
| authorships[1].countries | US |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I1311688040 |
| authorships[1].affiliations[0].raw_affiliation_string | Amazon Web Services AI, East Palo Alto, CA, USA |
| authorships[1].institutions[0].id | https://openalex.org/I1311688040 |
| authorships[1].institutions[0].ror | https://ror.org/04mv4n011 |
| authorships[1].institutions[0].type | company |
| authorships[1].institutions[0].lineage | https://openalex.org/I1311688040 |
| authorships[1].institutions[0].country_code | US |
| authorships[1].institutions[0].display_name | Amazon (United States) |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Aston Zhang |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Amazon Web Services AI, East Palo Alto, CA, USA |
| authorships[2].author.id | https://openalex.org/A5019647783 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-4067-4504 |
| authorships[2].author.display_name | Danilo Comminiello |
| authorships[2].countries | IT |
| authorships[2].affiliations[0].institution_ids | https://openalex.org/I861853513 |
| authorships[2].affiliations[0].raw_affiliation_string | Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Roma, Italy |
| authorships[2].institutions[0].id | https://openalex.org/I861853513 |
| authorships[2].institutions[0].ror | https://ror.org/02be6w209 |
| authorships[2].institutions[0].type | education |
| authorships[2].institutions[0].lineage | https://openalex.org/I861853513 |
| authorships[2].institutions[0].country_code | IT |
| authorships[2].institutions[0].display_name | Sapienza University of Rome |
| authorships[2].author_position | last |
| authorships[2].raw_author_name | Danilo Comminiello |
| authorships[2].is_corresponding | False |
| authorships[2].raw_affiliation_strings | Department of Information Engineering, Electronics and Telecommunications (DIET), Sapienza University of Rome, Roma, Italy |
| has_content.pdf | True |
| has_content.grobid_xml | True |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://ieeexplore.ieee.org/ielx7/5962385/6104215/09983846.pdf |
| open_access.oa_status | hybrid |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | PHNNs: Lightweight Neural Networks via Parameterized Hypercomplex Convolutions |
| 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 | 0.9997000098228455 |
| 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 | Neural Networks and Applications |
| related_works | https://openalex.org/W2044767466, https://openalex.org/W2800395957, https://openalex.org/W2026218351, https://openalex.org/W3185621658, https://openalex.org/W2507833514, https://openalex.org/W4388067726, https://openalex.org/W4224325206, https://openalex.org/W2916518000, https://openalex.org/W4401836278, https://openalex.org/W1578004053 |
| cited_by_count | 34 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 5 |
| counts_by_year[1].year | 2024 |
| counts_by_year[1].cited_by_count | 16 |
| counts_by_year[2].year | 2023 |
| counts_by_year[2].cited_by_count | 10 |
| counts_by_year[3].year | 2022 |
| counts_by_year[3].cited_by_count | 3 |
| locations_count | 3 |
| best_oa_location.id | doi:10.1109/tnnls.2022.3226772 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4210175523 |
| best_oa_location.source.issn | 2162-237X, 2162-2388 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | False |
| best_oa_location.source.issn_l | 2162-237X |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | IEEE Transactions on Neural Networks and Learning Systems |
| best_oa_location.source.host_organization | https://openalex.org/P4310319808 |
| best_oa_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| best_oa_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| best_oa_location.license | cc-by |
| best_oa_location.pdf_url | https://ieeexplore.ieee.org/ielx7/5962385/6104215/09983846.pdf |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | IEEE Transactions on Neural Networks and Learning Systems |
| best_oa_location.landing_page_url | https://doi.org/10.1109/tnnls.2022.3226772 |
| primary_location.id | doi:10.1109/tnnls.2022.3226772 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4210175523 |
| primary_location.source.issn | 2162-237X, 2162-2388 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | False |
| primary_location.source.issn_l | 2162-237X |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | IEEE Transactions on Neural Networks and Learning Systems |
| primary_location.source.host_organization | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_name | Institute of Electrical and Electronics Engineers |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310319808 |
| primary_location.source.host_organization_lineage_names | Institute of Electrical and Electronics Engineers |
| primary_location.license | cc-by |
| primary_location.pdf_url | https://ieeexplore.ieee.org/ielx7/5962385/6104215/09983846.pdf |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | IEEE Transactions on Neural Networks and Learning Systems |
| primary_location.landing_page_url | https://doi.org/10.1109/tnnls.2022.3226772 |
| publication_date | 2022-12-13 |
| publication_year | 2022 |
| referenced_works | https://openalex.org/W3035574324, https://openalex.org/W3137278571, https://openalex.org/W2965658867, https://openalex.org/W3126374782, https://openalex.org/W3047932858, https://openalex.org/W2892142366, https://openalex.org/W2963982127, https://openalex.org/W3015103190, https://openalex.org/W3215103204, https://openalex.org/W3197794951, https://openalex.org/W2611561008, https://openalex.org/W2766270357, https://openalex.org/W3004102150, https://openalex.org/W2981196140, https://openalex.org/W2091669036, https://openalex.org/W2062096799, https://openalex.org/W3162589478, https://openalex.org/W6752004172, https://openalex.org/W4210600196, https://openalex.org/W2952383053, https://openalex.org/W3210363450, https://openalex.org/W3006852363, https://openalex.org/W3004182051, https://openalex.org/W3205488134, https://openalex.org/W3163462841, https://openalex.org/W3180143978, https://openalex.org/W3154359097, https://openalex.org/W3091222154, https://openalex.org/W2940223958, https://openalex.org/W3196137477, https://openalex.org/W6790375383, https://openalex.org/W3015772761, https://openalex.org/W6763588080, https://openalex.org/W3186067722, https://openalex.org/W3080923968, https://openalex.org/W6788237939, https://openalex.org/W3204160375, https://openalex.org/W3166140588, https://openalex.org/W4214493665, https://openalex.org/W2526050071, https://openalex.org/W2966878259, https://openalex.org/W2963230471, https://openalex.org/W2084472453, https://openalex.org/W2963585199, https://openalex.org/W6637373629, https://openalex.org/W2194775991, https://openalex.org/W1576577473, https://openalex.org/W2905556235, https://openalex.org/W3094509890, https://openalex.org/W4311903586, https://openalex.org/W2810934215, https://openalex.org/W6801655670, https://openalex.org/W2962858109, https://openalex.org/W3178592608, https://openalex.org/W3212486120, https://openalex.org/W6769540564, https://openalex.org/W4205784559, https://openalex.org/W4288090629, https://openalex.org/W4226527255, https://openalex.org/W4286914341, https://openalex.org/W4287122891, https://openalex.org/W3197827948 |
| referenced_works_count | 62 |
| abstract_inverted_index.a | 80, 113, 142 |
| abstract_inverted_index.As | 141 |
| abstract_inverted_index.In | 37 |
| abstract_inverted_index.We | 162 |
| abstract_inverted_index.as | 127, 154 |
| abstract_inverted_index.by | 16, 31, 174 |
| abstract_inverted_index.in | 92, 119, 130, 158, 184 |
| abstract_inverted_index.is | 195 |
| abstract_inverted_index.of | 10, 20, 44, 52, 105, 147, 166, 172 |
| abstract_inverted_index.on | 177 |
| abstract_inverted_index.or | 95 |
| abstract_inverted_index.to | 5, 85, 90, 100, 169 |
| abstract_inverted_index.we | 40 |
| abstract_inverted_index.1-D | 99 |
| abstract_inverted_index.1/n | 151 |
| abstract_inverted_index.3-D | 136 |
| abstract_inverted_index.Our | 65 |
| abstract_inverted_index.and | 48, 61, 71, 181, 190 |
| abstract_inverted_index.any | 93 |
| abstract_inverted_index.are | 59, 88, 110 |
| abstract_inverted_index.at: | 197 |
| abstract_inverted_index.for | 135 |
| abstract_inverted_index.its | 156 |
| abstract_inverted_index.our | 186 |
| abstract_inverted_index.see | 102 |
| abstract_inverted_index.the | 7, 18, 42, 50, 68, 72, 107, 144, 159, 164 |
| abstract_inverted_index.Full | 193 |
| abstract_inverted_index.Such | 112 |
| abstract_inverted_index.been | 28 |
| abstract_inverted_index.code | 194 |
| abstract_inverted_index.data | 77 |
| abstract_inverted_index.free | 152 |
| abstract_inverted_index.from | 76, 98 |
| abstract_inverted_index.have | 3, 27 |
| abstract_inverted_index.like | 138 |
| abstract_inverted_index.real | 160, 189 |
| abstract_inverted_index.that | 58 |
| abstract_inverted_index.this | 38, 167 |
| abstract_inverted_index.with | 150 |
| abstract_inverted_index.PHNNs | 87, 148 |
| abstract_inverted_index.audio | 182 |
| abstract_inverted_index.color | 139 |
| abstract_inverted_index.done, | 128 |
| abstract_inverted_index.image | 179 |
| abstract_inverted_index.rules | 70, 109 |
| abstract_inverted_index.text] | 103 |
| abstract_inverted_index.their | 120 |
| abstract_inverted_index.tuned | 96 |
| abstract_inverted_index.which | 185 |
| abstract_inverted_index.while | 12 |
| abstract_inverted_index.(QNNs) | 134 |
| abstract_inverted_index.allows | 115 |
| abstract_inverted_index.analog | 157 |
| abstract_inverted_index.define | 41 |
| abstract_inverted_index.domain | 83, 122 |
| abstract_inverted_index.family | 51, 146 |
| abstract_inverted_index.filter | 73 |
| abstract_inverted_index.grasps | 67 |
| abstract_inverted_index.inputs | 118, 137 |
| abstract_inverted_index.layers | 26, 47 |
| abstract_inverted_index.linear | 25 |
| abstract_inverted_index.method | 66, 187 |
| abstract_inverted_index.neural | 1, 55, 132 |
| abstract_inverted_index.number | 9 |
| abstract_inverted_index.proven | 4 |
| abstract_inverted_index.reduce | 6 |
| abstract_inverted_index.(PHNNs) | 57 |
| abstract_inverted_index.algebra | 108 |
| abstract_inverted_index.domain, | 97 |
| abstract_inverted_index.domain. | 161 |
| abstract_inverted_index.domains | 171 |
| abstract_inverted_index.follow. | 86 |
| abstract_inverted_index.further | 29, 125 |
| abstract_inverted_index.images. | 140 |
| abstract_inverted_index.models. | 64 |
| abstract_inverted_index.natural | 121 |
| abstract_inverted_index.operate | 91 |
| abstract_inverted_index.overall | 8 |
| abstract_inverted_index.preset. | 111 |
| abstract_inverted_index.regards | 155 |
| abstract_inverted_index.result, | 143 |
| abstract_inverted_index.rigidly | 81 |
| abstract_inverted_index.various | 178 |
| abstract_inverted_index.whether | 106 |
| abstract_inverted_index.without | 78, 123 |
| abstract_inverted_index.Clifford | 21 |
| abstract_inverted_index.annexing | 124 |
| abstract_inverted_index.approach | 168 |
| abstract_inverted_index.article, | 39 |
| abstract_inverted_index.datasets | 180, 183 |
| abstract_inverted_index.directly | 75 |
| abstract_inverted_index.ensuring | 13 |
| abstract_inverted_index.flexible | 89 |
| abstract_inverted_index.improved | 30 |
| abstract_inverted_index.instead, | 129 |
| abstract_inverted_index.multiple | 170 |
| abstract_inverted_index.networks | 2, 56, 133 |
| abstract_inverted_index.operates | 149 |
| abstract_inverted_index.proposed | 145 |
| abstract_inverted_index.valuable | 14 |
| abstract_inverted_index.Kronecker | 35 |
| abstract_inverted_index.Recently, | 23 |
| abstract_inverted_index.[Formula: | 101 |
| abstract_inverted_index.algebras. | 22 |
| abstract_inverted_index.available | 196 |
| abstract_inverted_index.efficient | 33, 62 |
| abstract_inverted_index.introduce | 49 |
| abstract_inverted_index.involving | 32 |
| abstract_inverted_index.products. | 36 |
| abstract_inverted_index.requiring | 79 |
| abstract_inverted_index.structure | 84 |
| abstract_inverted_index.leveraging | 17 |
| abstract_inverted_index.parameters | 11, 153 |
| abstract_inverted_index.performing | 175 |
| abstract_inverted_index.predefined | 82 |
| abstract_inverted_index.processing | 116 |
| abstract_inverted_index.properties | 19 |
| abstract_inverted_index.quaternion | 131 |
| abstract_inverted_index.regardless | 104 |
| abstract_inverted_index.application | 173 |
| abstract_inverted_index.convolution | 69 |
| abstract_inverted_index.demonstrate | 163 |
| abstract_inverted_index.dimensions, | 126 |
| abstract_inverted_index.experiments | 176 |
| abstract_inverted_index.large-scale | 63 |
| abstract_inverted_index.lightweight | 60 |
| abstract_inverted_index.outperforms | 188 |
| abstract_inverted_index.performance | 15 |
| abstract_inverted_index.versatility | 165 |
| abstract_inverted_index.Hypercomplex | 0 |
| abstract_inverted_index.hypercomplex | 24, 45, 54 |
| abstract_inverted_index.malleability | 114 |
| abstract_inverted_index.organization | 74 |
| abstract_inverted_index.user-defined | 94 |
| abstract_inverted_index.convolutional | 46 |
| abstract_inverted_index.counterparts. | 192 |
| abstract_inverted_index.parameterized | 34, 53 |
| abstract_inverted_index.multidimensional | 117 |
| abstract_inverted_index.parameterization | 43 |
| abstract_inverted_index.quaternion-valued | 191 |
| abstract_inverted_index.https://github.com/eleGAN23/HyperNets. | 198 |
| cited_by_percentile_year.max | 100 |
| cited_by_percentile_year.min | 96 |
| countries_distinct_count | 2 |
| institutions_distinct_count | 3 |
| citation_normalized_percentile.value | 0.95787017 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | True |