Optimizing optical neural network design for enhanced compatibility with analog computation Article Swipe
Zhaolin Lu
,
Jinming Tao
,
Xiaoyu Wang
,
Jianguo Liu
,
Leilei Wang
,
Shiyu Mei
,
Buwen Cheng
,
Jinye Li
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1364/oe.550613
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.1364/oe.550613
This paper breaks away from traditional approaches that merely emulate digital neural networks. Using Mach-Zehnder interferometer (MZI) networks as a case study, we explore the impact of the inherent properties of analog computation on performance and identify the characteristics that optical neural networks (ONNs) components should possess to better adapt to these specific properties. Specifically, we examine the influence of analog computation on bias power and activation functions, as well as the impact of optical pruning on ONN’s performance. The results show that a suitably larger bias power relative to normalized data and concave activation functions are more compatible with the characteristics of ONNs. These factors can significantly improve classification accuracy across different datasets and ξ values, with improvements reaching up to 35%. Additionally, optical pruning reduces the number of MZIs by two-thirds while maintaining performance. Moreover, these measures significantly enhance the robustness of ONNs against MZI losses and phase errors. Although this research primarily focuses on feedforward MZI-based networks, the proposed design principles are widely applicable to other types of ONNs.
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://doi.org/10.1364/oe.550613
- OA Status
- gold
- Cited By
- 4
- References
- 21
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4406105605
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4406105605Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.1364/oe.550613Digital Object Identifier
- Title
-
Optimizing optical neural network design for enhanced compatibility with analog computationWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-06Full publication date if available
- Authors
-
Zhaolin Lu, Jinming Tao, Xiaoyu Wang, Jianguo Liu, Leilei Wang, Shiyu Mei, Buwen Cheng, Jinye LiList of authors in order
- Landing page
-
https://doi.org/10.1364/oe.550613Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
goldOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.1364/oe.550613Direct OA link when available
- Concepts
-
Compatibility (geochemistry), Optics, Computer science, Computation, Artificial neural network, Materials science, Artificial intelligence, Physics, Algorithm, Composite materialTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
4Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 4Per-year citation counts (last 5 years)
- References (count)
-
21Number of works referenced by this work
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4406105605 |
|---|---|
| doi | https://doi.org/10.1364/oe.550613 |
| ids.doi | https://doi.org/10.1364/oe.550613 |
| ids.pmid | https://pubmed.ncbi.nlm.nih.gov/39876398 |
| ids.openalex | https://openalex.org/W4406105605 |
| fwci | 19.27898059 |
| type | article |
| title | Optimizing optical neural network design for enhanced compatibility with analog computation |
| awards[0].id | https://openalex.org/G6853269808 |
| awards[0].funder_id | https://openalex.org/F4320321001 |
| awards[0].display_name | |
| awards[0].funder_award_id | 12374397 |
| awards[0].funder_display_name | National Natural Science Foundation of China |
| biblio.issue | 2 |
| biblio.volume | 33 |
| biblio.last_page | 2499 |
| biblio.first_page | 2499 |
| topics[0].id | https://openalex.org/T12611 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 1.0 |
| 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 Reservoir Computing |
| topics[1].id | https://openalex.org/T10232 |
| topics[1].field.id | https://openalex.org/fields/22 |
| topics[1].field.display_name | Engineering |
| topics[1].score | 0.9990000128746033 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/2208 |
| topics[1].subfield.display_name | Electrical and Electronic Engineering |
| topics[1].display_name | Optical Network Technologies |
| topics[2].id | https://openalex.org/T10299 |
| topics[2].field.id | https://openalex.org/fields/22 |
| topics[2].field.display_name | Engineering |
| topics[2].score | 0.9983999729156494 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2208 |
| topics[2].subfield.display_name | Electrical and Electronic Engineering |
| topics[2].display_name | Photonic and Optical Devices |
| funders[0].id | https://openalex.org/F4320321001 |
| funders[0].ror | https://ror.org/01h0zpd94 |
| funders[0].display_name | National Natural Science Foundation of China |
| is_xpac | False |
| apc_list.value | 2270 |
| apc_list.currency | USD |
| apc_list.value_usd | 2270 |
| apc_paid.value | 2270 |
| apc_paid.currency | USD |
| apc_paid.value_usd | 2270 |
| concepts[0].id | https://openalex.org/C2778648169 |
| concepts[0].level | 2 |
| concepts[0].score | 0.741112470626831 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q967768 |
| concepts[0].display_name | Compatibility (geochemistry) |
| concepts[1].id | https://openalex.org/C120665830 |
| concepts[1].level | 1 |
| concepts[1].score | 0.5628920793533325 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q14620 |
| concepts[1].display_name | Optics |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.5206769704818726 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C45374587 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4755387306213379 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q12525525 |
| concepts[3].display_name | Computation |
| concepts[4].id | https://openalex.org/C50644808 |
| concepts[4].level | 2 |
| concepts[4].score | 0.46643733978271484 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[4].display_name | Artificial neural network |
| concepts[5].id | https://openalex.org/C192562407 |
| concepts[5].level | 0 |
| concepts[5].score | 0.2922038435935974 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q228736 |
| concepts[5].display_name | Materials science |
| concepts[6].id | https://openalex.org/C154945302 |
| concepts[6].level | 1 |
| concepts[6].score | 0.20338118076324463 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[6].display_name | Artificial intelligence |
| concepts[7].id | https://openalex.org/C121332964 |
| concepts[7].level | 0 |
| concepts[7].score | 0.16942548751831055 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[7].display_name | Physics |
| concepts[8].id | https://openalex.org/C11413529 |
| concepts[8].level | 1 |
| concepts[8].score | 0.14364764094352722 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[8].display_name | Algorithm |
| concepts[9].id | https://openalex.org/C159985019 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q181790 |
| concepts[9].display_name | Composite material |
| keywords[0].id | https://openalex.org/keywords/compatibility |
| keywords[0].score | 0.741112470626831 |
| keywords[0].display_name | Compatibility (geochemistry) |
| keywords[1].id | https://openalex.org/keywords/optics |
| keywords[1].score | 0.5628920793533325 |
| keywords[1].display_name | Optics |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.5206769704818726 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/computation |
| keywords[3].score | 0.4755387306213379 |
| keywords[3].display_name | Computation |
| keywords[4].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[4].score | 0.46643733978271484 |
| keywords[4].display_name | Artificial neural network |
| keywords[5].id | https://openalex.org/keywords/materials-science |
| keywords[5].score | 0.2922038435935974 |
| keywords[5].display_name | Materials science |
| keywords[6].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[6].score | 0.20338118076324463 |
| keywords[6].display_name | Artificial intelligence |
| keywords[7].id | https://openalex.org/keywords/physics |
| keywords[7].score | 0.16942548751831055 |
| keywords[7].display_name | Physics |
| keywords[8].id | https://openalex.org/keywords/algorithm |
| keywords[8].score | 0.14364764094352722 |
| keywords[8].display_name | Algorithm |
| language | en |
| locations[0].id | doi:10.1364/oe.550613 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S178776955 |
| locations[0].source.issn | 1094-4087 |
| locations[0].source.type | journal |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | 1094-4087 |
| locations[0].source.is_core | True |
| locations[0].source.is_in_doaj | True |
| locations[0].source.display_name | Optics Express |
| locations[0].source.host_organization | https://openalex.org/P4310315679 |
| locations[0].source.host_organization_name | Optica Publishing Group |
| locations[0].source.host_organization_lineage | https://openalex.org/P4310315679 |
| locations[0].source.host_organization_lineage_names | Optica Publishing Group |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | publishedVersion |
| locations[0].raw_type | journal-article |
| locations[0].license_id | |
| locations[0].is_accepted | True |
| locations[0].is_published | True |
| locations[0].raw_source_name | Optics Express |
| locations[0].landing_page_url | https://doi.org/10.1364/oe.550613 |
| locations[1].id | pmid:39876398 |
| 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 | Optics express |
| locations[1].landing_page_url | https://pubmed.ncbi.nlm.nih.gov/39876398 |
| indexed_in | crossref, doaj, pubmed |
| authorships[0].author.id | https://openalex.org/A5017734160 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-8973-8049 |
| authorships[0].author.display_name | Zhaolin Lu |
| authorships[0].countries | CN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I4210165038 |
| authorships[0].affiliations[0].raw_affiliation_string | University of Chinese Academy of Sciences |
| authorships[0].institutions[0].id | https://openalex.org/I4210165038 |
| authorships[0].institutions[0].ror | https://ror.org/05qbk4x57 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I19820366, https://openalex.org/I4210165038 |
| authorships[0].institutions[0].country_code | CN |
| authorships[0].institutions[0].display_name | University of Chinese Academy of Sciences |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zongyu Lu |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | University of Chinese Academy of Sciences |
| authorships[1].author.id | https://openalex.org/A5025594064 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-3853-8079 |
| authorships[1].author.display_name | Jinming Tao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Jinming Tao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100357642 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1625-231X |
| authorships[2].author.display_name | Xiaoyu Wang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Xiaoyu Wang |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100780350 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-7051-4272 |
| authorships[3].author.display_name | Jianguo Liu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Jianguo Liu |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5100400334 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-9008-0822 |
| authorships[4].author.display_name | Leilei Wang |
| authorships[4].countries | CN |
| authorships[4].affiliations[0].institution_ids | https://openalex.org/I157773358 |
| authorships[4].affiliations[0].raw_affiliation_string | Sun Yat-sen University |
| authorships[4].institutions[0].id | https://openalex.org/I157773358 |
| authorships[4].institutions[0].ror | https://ror.org/0064kty71 |
| authorships[4].institutions[0].type | education |
| authorships[4].institutions[0].lineage | https://openalex.org/I157773358 |
| authorships[4].institutions[0].country_code | CN |
| authorships[4].institutions[0].display_name | Sun Yat-sen University |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Leilei Wang |
| authorships[4].is_corresponding | False |
| authorships[4].raw_affiliation_strings | Sun Yat-sen University |
| authorships[5].author.id | https://openalex.org/A5009940245 |
| authorships[5].author.orcid | |
| authorships[5].author.display_name | Shiyu Mei |
| authorships[5].countries | CN |
| authorships[5].affiliations[0].institution_ids | https://openalex.org/I4210165038 |
| authorships[5].affiliations[0].raw_affiliation_string | University of Chinese Academy of Sciences |
| authorships[5].institutions[0].id | https://openalex.org/I4210165038 |
| authorships[5].institutions[0].ror | https://ror.org/05qbk4x57 |
| authorships[5].institutions[0].type | education |
| authorships[5].institutions[0].lineage | https://openalex.org/I19820366, https://openalex.org/I4210165038 |
| authorships[5].institutions[0].country_code | CN |
| authorships[5].institutions[0].display_name | University of Chinese Academy of Sciences |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Shiyu Mei |
| authorships[5].is_corresponding | False |
| authorships[5].raw_affiliation_strings | University of Chinese Academy of Sciences |
| authorships[6].author.id | https://openalex.org/A5047558399 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-6547-1458 |
| authorships[6].author.display_name | Buwen Cheng |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Buwen Cheng |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5032409084 |
| authorships[7].author.orcid | |
| authorships[7].author.display_name | Jinye Li |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Jinye Li |
| authorships[7].is_corresponding | False |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.1364/oe.550613 |
| open_access.oa_status | gold |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Optimizing optical neural network design for enhanced compatibility with analog computation |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T03:46:38.306776 |
| primary_topic.id | https://openalex.org/T12611 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 1.0 |
| 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 Reservoir Computing |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390255551, https://openalex.org/W2367511445, https://openalex.org/W2381930792, https://openalex.org/W2358901819, https://openalex.org/W745733672, https://openalex.org/W2983545107, https://openalex.org/W2389102290 |
| cited_by_count | 4 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 4 |
| locations_count | 2 |
| best_oa_location.id | doi:10.1364/oe.550613 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S178776955 |
| best_oa_location.source.issn | 1094-4087 |
| best_oa_location.source.type | journal |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | 1094-4087 |
| best_oa_location.source.is_core | True |
| best_oa_location.source.is_in_doaj | True |
| best_oa_location.source.display_name | Optics Express |
| best_oa_location.source.host_organization | https://openalex.org/P4310315679 |
| best_oa_location.source.host_organization_name | Optica Publishing Group |
| best_oa_location.source.host_organization_lineage | https://openalex.org/P4310315679 |
| best_oa_location.source.host_organization_lineage_names | Optica Publishing Group |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| best_oa_location.version | publishedVersion |
| best_oa_location.raw_type | journal-article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | True |
| best_oa_location.is_published | True |
| best_oa_location.raw_source_name | Optics Express |
| best_oa_location.landing_page_url | https://doi.org/10.1364/oe.550613 |
| primary_location.id | doi:10.1364/oe.550613 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S178776955 |
| primary_location.source.issn | 1094-4087 |
| primary_location.source.type | journal |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | 1094-4087 |
| primary_location.source.is_core | True |
| primary_location.source.is_in_doaj | True |
| primary_location.source.display_name | Optics Express |
| primary_location.source.host_organization | https://openalex.org/P4310315679 |
| primary_location.source.host_organization_name | Optica Publishing Group |
| primary_location.source.host_organization_lineage | https://openalex.org/P4310315679 |
| primary_location.source.host_organization_lineage_names | Optica Publishing Group |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | publishedVersion |
| primary_location.raw_type | journal-article |
| primary_location.license_id | |
| primary_location.is_accepted | True |
| primary_location.is_published | True |
| primary_location.raw_source_name | Optics Express |
| primary_location.landing_page_url | https://doi.org/10.1364/oe.550613 |
| publication_date | 2025-01-06 |
| publication_year | 2025 |
| referenced_works | https://openalex.org/W3096230432, https://openalex.org/W3165876013, https://openalex.org/W4309746926, https://openalex.org/W2752849906, https://openalex.org/W4281845262, https://openalex.org/W4377982009, https://openalex.org/W4387451994, https://openalex.org/W4384282348, https://openalex.org/W3194056411, https://openalex.org/W3121141908, https://openalex.org/W2964082513, https://openalex.org/W4403559983, https://openalex.org/W4380628213, https://openalex.org/W4367173722, https://openalex.org/W2112796928, https://openalex.org/W2913860539, https://openalex.org/W2076476236, https://openalex.org/W2962730419, https://openalex.org/W2001619934, https://openalex.org/W2982846042, https://openalex.org/W3128451613 |
| referenced_works_count | 21 |
| abstract_inverted_index.a | 19, 83 |
| abstract_inverted_index.as | 18, 68, 70 |
| abstract_inverted_index.by | 131 |
| abstract_inverted_index.of | 26, 30, 59, 73, 102, 129, 143, 170 |
| abstract_inverted_index.on | 33, 62, 76, 156 |
| abstract_inverted_index.to | 47, 50, 89, 121, 167 |
| abstract_inverted_index.up | 120 |
| abstract_inverted_index.we | 22, 55 |
| abstract_inverted_index.ξ | 115 |
| abstract_inverted_index.MZI | 146 |
| abstract_inverted_index.The | 79 |
| abstract_inverted_index.and | 35, 65, 92, 114, 148 |
| abstract_inverted_index.are | 96, 164 |
| abstract_inverted_index.can | 106 |
| abstract_inverted_index.the | 24, 27, 37, 57, 71, 100, 127, 141, 160 |
| abstract_inverted_index.35%. | 122 |
| abstract_inverted_index.MZIs | 130 |
| abstract_inverted_index.ONNs | 144 |
| abstract_inverted_index.This | 0 |
| abstract_inverted_index.away | 3 |
| abstract_inverted_index.bias | 63, 86 |
| abstract_inverted_index.case | 20 |
| abstract_inverted_index.data | 91 |
| abstract_inverted_index.from | 4 |
| abstract_inverted_index.more | 97 |
| abstract_inverted_index.show | 81 |
| abstract_inverted_index.that | 7, 39, 82 |
| abstract_inverted_index.this | 152 |
| abstract_inverted_index.well | 69 |
| abstract_inverted_index.with | 99, 117 |
| abstract_inverted_index.(MZI) | 16 |
| abstract_inverted_index.ONNs. | 103, 171 |
| abstract_inverted_index.These | 104 |
| abstract_inverted_index.Using | 13 |
| abstract_inverted_index.adapt | 49 |
| abstract_inverted_index.other | 168 |
| abstract_inverted_index.paper | 1 |
| abstract_inverted_index.phase | 149 |
| abstract_inverted_index.power | 64, 87 |
| abstract_inverted_index.these | 51, 137 |
| abstract_inverted_index.types | 169 |
| abstract_inverted_index.while | 133 |
| abstract_inverted_index.(ONNs) | 43 |
| abstract_inverted_index.across | 111 |
| abstract_inverted_index.analog | 31, 60 |
| abstract_inverted_index.better | 48 |
| abstract_inverted_index.breaks | 2 |
| abstract_inverted_index.design | 162 |
| abstract_inverted_index.impact | 25, 72 |
| abstract_inverted_index.larger | 85 |
| abstract_inverted_index.losses | 147 |
| abstract_inverted_index.merely | 8 |
| abstract_inverted_index.neural | 11, 41 |
| abstract_inverted_index.number | 128 |
| abstract_inverted_index.should | 45 |
| abstract_inverted_index.study, | 21 |
| abstract_inverted_index.widely | 165 |
| abstract_inverted_index.ONN’s | 77 |
| abstract_inverted_index.against | 145 |
| abstract_inverted_index.concave | 93 |
| abstract_inverted_index.digital | 10 |
| abstract_inverted_index.emulate | 9 |
| abstract_inverted_index.enhance | 140 |
| abstract_inverted_index.errors. | 150 |
| abstract_inverted_index.examine | 56 |
| abstract_inverted_index.explore | 23 |
| abstract_inverted_index.factors | 105 |
| abstract_inverted_index.focuses | 155 |
| abstract_inverted_index.improve | 108 |
| abstract_inverted_index.optical | 40, 74, 124 |
| abstract_inverted_index.possess | 46 |
| abstract_inverted_index.pruning | 75, 125 |
| abstract_inverted_index.reduces | 126 |
| abstract_inverted_index.results | 80 |
| abstract_inverted_index.values, | 116 |
| abstract_inverted_index.Although | 151 |
| abstract_inverted_index.accuracy | 110 |
| abstract_inverted_index.datasets | 113 |
| abstract_inverted_index.identify | 36 |
| abstract_inverted_index.inherent | 28 |
| abstract_inverted_index.measures | 138 |
| abstract_inverted_index.networks | 17, 42 |
| abstract_inverted_index.proposed | 161 |
| abstract_inverted_index.reaching | 119 |
| abstract_inverted_index.relative | 88 |
| abstract_inverted_index.research | 153 |
| abstract_inverted_index.specific | 52 |
| abstract_inverted_index.suitably | 84 |
| abstract_inverted_index.MZI-based | 158 |
| abstract_inverted_index.Moreover, | 136 |
| abstract_inverted_index.different | 112 |
| abstract_inverted_index.functions | 95 |
| abstract_inverted_index.influence | 58 |
| abstract_inverted_index.networks, | 159 |
| abstract_inverted_index.networks. | 12 |
| abstract_inverted_index.primarily | 154 |
| abstract_inverted_index.activation | 66, 94 |
| abstract_inverted_index.applicable | 166 |
| abstract_inverted_index.approaches | 6 |
| abstract_inverted_index.compatible | 98 |
| abstract_inverted_index.components | 44 |
| abstract_inverted_index.functions, | 67 |
| abstract_inverted_index.normalized | 90 |
| abstract_inverted_index.principles | 163 |
| abstract_inverted_index.properties | 29 |
| abstract_inverted_index.robustness | 142 |
| abstract_inverted_index.two-thirds | 132 |
| abstract_inverted_index.computation | 32, 61 |
| abstract_inverted_index.feedforward | 157 |
| abstract_inverted_index.maintaining | 134 |
| abstract_inverted_index.performance | 34 |
| abstract_inverted_index.properties. | 53 |
| abstract_inverted_index.traditional | 5 |
| abstract_inverted_index.Mach-Zehnder | 14 |
| abstract_inverted_index.improvements | 118 |
| abstract_inverted_index.performance. | 78, 135 |
| abstract_inverted_index.Additionally, | 123 |
| abstract_inverted_index.Specifically, | 54 |
| abstract_inverted_index.significantly | 107, 139 |
| abstract_inverted_index.classification | 109 |
| abstract_inverted_index.interferometer | 15 |
| abstract_inverted_index.characteristics | 38, 101 |
| cited_by_percentile_year.max | 98 |
| cited_by_percentile_year.min | 97 |
| countries_distinct_count | 1 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile.value | 0.98661954 |
| citation_normalized_percentile.is_in_top_1_percent | True |
| citation_normalized_percentile.is_in_top_10_percent | True |