Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks Article Swipe
Anzhe Cheng
,
Zhenkun Wang
,
Chenzhong Yin
,
Mingxi Cheng
,
Heng Ping
,
Xiongye Xiao
,
Shahin Nazarian
,
Paul Bogdan
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2312.13311
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2312.13311
Backpropagation (BP) has been a successful optimization technique for deep learning models. However, its limitations, such as backward- and update-locking, and its biological implausibility, hinder the concurrent updating of layers and do not mimic the local learning processes observed in the human brain. To address these issues, recent research has suggested using local error signals to asynchronously train network blocks. However, this approach often involves extensive trial-and-error iterations to determine the best configuration for local training. This includes decisions on how to decouple network blocks and which auxiliary networks to use for each block. In our work, we introduce a novel BP-free approach: a block-wise BP-free (BWBPF) neural network that leverages local error signals to optimize distinct sub-neural networks separately, where the global loss is only responsible for updating the output layer. The local error signals used in the BP-free model can be computed in parallel, enabling a potential speed-up in the weight update process through parallel implementation. Our experimental results consistently show that this approach can identify transferable decoupled architectures for VGG and ResNet variations, outperforming models trained with end-to-end backpropagation and other state-of-the-art block-wise learning techniques on datasets such as CIFAR-10 and Tiny-ImageNet. The code is released at https://github.com/Belis0811/BWBPF.
Related Topics
Concepts
Backpropagation
Computer science
Block (permutation group theory)
Artificial neural network
Code (set theory)
Artificial intelligence
Process (computing)
Deep learning
Machine learning
Layer (electronics)
Set (abstract data type)
Geometry
Programming language
Organic chemistry
Chemistry
Mathematics
Operating system
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2312.13311
- https://arxiv.org/pdf/2312.13311
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4390136289
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4390136289Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2312.13311Digital Object Identifier
- Title
-
Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-12-20Full publication date if available
- Authors
-
Anzhe Cheng, Zhenkun Wang, Chenzhong Yin, Mingxi Cheng, Heng Ping, Xiongye Xiao, Shahin Nazarian, Paul BogdanList of authors in order
- Landing page
-
https://arxiv.org/abs/2312.13311Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2312.13311Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2312.13311Direct OA link when available
- Concepts
-
Backpropagation, Computer science, Block (permutation group theory), Artificial neural network, Code (set theory), Artificial intelligence, Process (computing), Deep learning, Machine learning, Layer (electronics), Set (abstract data type), Geometry, Programming language, Organic chemistry, Chemistry, Mathematics, Operating systemTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4390136289 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2312.13311 |
| ids.doi | https://doi.org/10.48550/arxiv.2312.13311 |
| ids.openalex | https://openalex.org/W4390136289 |
| fwci | |
| type | preprint |
| title | Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10502 |
| topics[0].field.id | https://openalex.org/fields/22 |
| topics[0].field.display_name | Engineering |
| topics[0].score | 0.9984999895095825 |
| topics[0].domain.id | https://openalex.org/domains/3 |
| topics[0].domain.display_name | Physical Sciences |
| topics[0].subfield.id | https://openalex.org/subfields/2208 |
| topics[0].subfield.display_name | Electrical and Electronic Engineering |
| topics[0].display_name | Advanced Memory and Neural Computing |
| topics[1].id | https://openalex.org/T10036 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9965000152587891 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1707 |
| topics[1].subfield.display_name | Computer Vision and Pattern Recognition |
| topics[1].display_name | Advanced Neural Network Applications |
| topics[2].id | https://openalex.org/T10429 |
| topics[2].field.id | https://openalex.org/fields/28 |
| topics[2].field.display_name | Neuroscience |
| topics[2].score | 0.9936000108718872 |
| topics[2].domain.id | https://openalex.org/domains/1 |
| topics[2].domain.display_name | Life Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/2805 |
| topics[2].subfield.display_name | Cognitive Neuroscience |
| topics[2].display_name | EEG and Brain-Computer Interfaces |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C155032097 |
| concepts[0].level | 3 |
| concepts[0].score | 0.8469113111495972 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q798503 |
| concepts[0].display_name | Backpropagation |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.8098554015159607 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C2777210771 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7761361598968506 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q4927124 |
| concepts[2].display_name | Block (permutation group theory) |
| concepts[3].id | https://openalex.org/C50644808 |
| concepts[3].level | 2 |
| concepts[3].score | 0.768915057182312 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[3].display_name | Artificial neural network |
| concepts[4].id | https://openalex.org/C2776760102 |
| concepts[4].level | 3 |
| concepts[4].score | 0.6433406472206116 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q5139990 |
| concepts[4].display_name | Code (set theory) |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.6398004293441772 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C98045186 |
| concepts[6].level | 2 |
| concepts[6].score | 0.6200402975082397 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q205663 |
| concepts[6].display_name | Process (computing) |
| concepts[7].id | https://openalex.org/C108583219 |
| concepts[7].level | 2 |
| concepts[7].score | 0.5923393964767456 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[7].display_name | Deep learning |
| concepts[8].id | https://openalex.org/C119857082 |
| concepts[8].level | 1 |
| concepts[8].score | 0.45006150007247925 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[8].display_name | Machine learning |
| concepts[9].id | https://openalex.org/C2779227376 |
| concepts[9].level | 2 |
| concepts[9].score | 0.43829867243766785 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q6505497 |
| concepts[9].display_name | Layer (electronics) |
| concepts[10].id | https://openalex.org/C177264268 |
| concepts[10].level | 2 |
| concepts[10].score | 0.12399673461914062 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q1514741 |
| concepts[10].display_name | Set (abstract data type) |
| concepts[11].id | https://openalex.org/C2524010 |
| concepts[11].level | 1 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q8087 |
| concepts[11].display_name | Geometry |
| concepts[12].id | https://openalex.org/C199360897 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[12].display_name | Programming language |
| concepts[13].id | https://openalex.org/C178790620 |
| concepts[13].level | 1 |
| concepts[13].score | 0.0 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q11351 |
| concepts[13].display_name | Organic chemistry |
| 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/C33923547 |
| concepts[15].level | 0 |
| concepts[15].score | 0.0 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[15].display_name | Mathematics |
| concepts[16].id | https://openalex.org/C111919701 |
| concepts[16].level | 1 |
| concepts[16].score | 0.0 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[16].display_name | Operating system |
| keywords[0].id | https://openalex.org/keywords/backpropagation |
| keywords[0].score | 0.8469113111495972 |
| keywords[0].display_name | Backpropagation |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.8098554015159607 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/block |
| keywords[2].score | 0.7761361598968506 |
| keywords[2].display_name | Block (permutation group theory) |
| keywords[3].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[3].score | 0.768915057182312 |
| keywords[3].display_name | Artificial neural network |
| keywords[4].id | https://openalex.org/keywords/code |
| keywords[4].score | 0.6433406472206116 |
| keywords[4].display_name | Code (set theory) |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.6398004293441772 |
| keywords[5].display_name | Artificial intelligence |
| keywords[6].id | https://openalex.org/keywords/process |
| keywords[6].score | 0.6200402975082397 |
| keywords[6].display_name | Process (computing) |
| keywords[7].id | https://openalex.org/keywords/deep-learning |
| keywords[7].score | 0.5923393964767456 |
| keywords[7].display_name | Deep learning |
| keywords[8].id | https://openalex.org/keywords/machine-learning |
| keywords[8].score | 0.45006150007247925 |
| keywords[8].display_name | Machine learning |
| keywords[9].id | https://openalex.org/keywords/layer |
| keywords[9].score | 0.43829867243766785 |
| keywords[9].display_name | Layer (electronics) |
| keywords[10].id | https://openalex.org/keywords/set |
| keywords[10].score | 0.12399673461914062 |
| keywords[10].display_name | Set (abstract data type) |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2312.13311 |
| 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 | cc-by |
| locations[0].pdf_url | https://arxiv.org/pdf/2312.13311 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2312.13311 |
| locations[1].id | doi:10.48550/arxiv.2312.13311 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2312.13311 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5108222356 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Anzhe Cheng |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Cheng, Anzhe |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5064608174 |
| authorships[1].author.orcid | https://orcid.org/0000-0003-1152-6780 |
| authorships[1].author.display_name | Zhenkun Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wang, Zhenkun |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5037487522 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-6411-7441 |
| authorships[2].author.display_name | Chenzhong Yin |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Yin, Chenzhong |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5057367919 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8070-6665 |
| authorships[3].author.display_name | Mingxi Cheng |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Cheng, Mingxi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5011759850 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Heng Ping |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Ping, Heng |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5004690249 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-3181-7166 |
| authorships[5].author.display_name | Xiongye Xiao |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Xiao, Xiongye |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5065681916 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Shahin Nazarian |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Nazarian, Shahin |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5105925385 |
| authorships[7].author.orcid | https://orcid.org/0000-0003-2118-0816 |
| authorships[7].author.display_name | Paul Bogdan |
| authorships[7].author_position | last |
| authorships[7].raw_author_name | Bogdan, Paul |
| authorships[7].is_corresponding | False |
| 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/2312.13311 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Unlocking Deep Learning: A BP-Free Approach for Parallel Block-Wise Training of Neural Networks |
| has_fulltext | True |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10502 |
| primary_topic.field.id | https://openalex.org/fields/22 |
| primary_topic.field.display_name | Engineering |
| primary_topic.score | 0.9984999895095825 |
| primary_topic.domain.id | https://openalex.org/domains/3 |
| primary_topic.domain.display_name | Physical Sciences |
| primary_topic.subfield.id | https://openalex.org/subfields/2208 |
| primary_topic.subfield.display_name | Electrical and Electronic Engineering |
| primary_topic.display_name | Advanced Memory and Neural Computing |
| related_works | https://openalex.org/W4239286941, https://openalex.org/W2088845016, https://openalex.org/W589102260, https://openalex.org/W1966421350, https://openalex.org/W1868434454, https://openalex.org/W4366985237, https://openalex.org/W2810569973, https://openalex.org/W2128396103, https://openalex.org/W4366984740, https://openalex.org/W4367299891 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2312.13311 |
| 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 | cc-by |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2312.13311 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by |
| 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/2312.13311 |
| primary_location.id | pmh:oai:arXiv.org:2312.13311 |
| 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 | cc-by |
| primary_location.pdf_url | https://arxiv.org/pdf/2312.13311 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2312.13311 |
| publication_date | 2023-12-20 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 4, 99, 103, 147 |
| abstract_inverted_index.In | 94 |
| abstract_inverted_index.To | 43 |
| abstract_inverted_index.as | 16, 191 |
| abstract_inverted_index.at | 199 |
| abstract_inverted_index.be | 142 |
| abstract_inverted_index.do | 31 |
| abstract_inverted_index.in | 39, 137, 144, 150 |
| abstract_inverted_index.is | 124, 197 |
| abstract_inverted_index.of | 28 |
| abstract_inverted_index.on | 79, 188 |
| abstract_inverted_index.to | 55, 68, 81, 89, 114 |
| abstract_inverted_index.we | 97 |
| abstract_inverted_index.Our | 158 |
| abstract_inverted_index.The | 132, 195 |
| abstract_inverted_index.VGG | 172 |
| abstract_inverted_index.and | 18, 20, 30, 85, 173, 182, 193 |
| abstract_inverted_index.can | 141, 166 |
| abstract_inverted_index.for | 8, 73, 91, 127, 171 |
| abstract_inverted_index.has | 2, 49 |
| abstract_inverted_index.how | 80 |
| abstract_inverted_index.its | 13, 21 |
| abstract_inverted_index.not | 32 |
| abstract_inverted_index.our | 95 |
| abstract_inverted_index.the | 25, 34, 40, 70, 121, 129, 138, 151 |
| abstract_inverted_index.use | 90 |
| abstract_inverted_index.(BP) | 1 |
| abstract_inverted_index.This | 76 |
| abstract_inverted_index.been | 3 |
| abstract_inverted_index.best | 71 |
| abstract_inverted_index.code | 196 |
| abstract_inverted_index.deep | 9 |
| abstract_inverted_index.each | 92 |
| abstract_inverted_index.loss | 123 |
| abstract_inverted_index.only | 125 |
| abstract_inverted_index.show | 162 |
| abstract_inverted_index.such | 15, 190 |
| abstract_inverted_index.that | 109, 163 |
| abstract_inverted_index.this | 61, 164 |
| abstract_inverted_index.used | 136 |
| abstract_inverted_index.with | 179 |
| abstract_inverted_index.error | 53, 112, 134 |
| abstract_inverted_index.human | 41 |
| abstract_inverted_index.local | 35, 52, 74, 111, 133 |
| abstract_inverted_index.mimic | 33 |
| abstract_inverted_index.model | 140 |
| abstract_inverted_index.novel | 100 |
| abstract_inverted_index.often | 63 |
| abstract_inverted_index.other | 183 |
| abstract_inverted_index.these | 45 |
| abstract_inverted_index.train | 57 |
| abstract_inverted_index.using | 51 |
| abstract_inverted_index.where | 120 |
| abstract_inverted_index.which | 86 |
| abstract_inverted_index.work, | 96 |
| abstract_inverted_index.ResNet | 174 |
| abstract_inverted_index.block. | 93 |
| abstract_inverted_index.blocks | 84 |
| abstract_inverted_index.brain. | 42 |
| abstract_inverted_index.global | 122 |
| abstract_inverted_index.hinder | 24 |
| abstract_inverted_index.layer. | 131 |
| abstract_inverted_index.layers | 29 |
| abstract_inverted_index.models | 177 |
| abstract_inverted_index.neural | 107 |
| abstract_inverted_index.output | 130 |
| abstract_inverted_index.recent | 47 |
| abstract_inverted_index.update | 153 |
| abstract_inverted_index.weight | 152 |
| abstract_inverted_index.(BWBPF) | 106 |
| abstract_inverted_index.BP-free | 101, 105, 139 |
| abstract_inverted_index.address | 44 |
| abstract_inverted_index.blocks. | 59 |
| abstract_inverted_index.issues, | 46 |
| abstract_inverted_index.models. | 11 |
| abstract_inverted_index.network | 58, 83, 108 |
| abstract_inverted_index.process | 154 |
| abstract_inverted_index.results | 160 |
| abstract_inverted_index.signals | 54, 113, 135 |
| abstract_inverted_index.through | 155 |
| abstract_inverted_index.trained | 178 |
| abstract_inverted_index.CIFAR-10 | 192 |
| abstract_inverted_index.However, | 12, 60 |
| abstract_inverted_index.approach | 62, 165 |
| abstract_inverted_index.computed | 143 |
| abstract_inverted_index.datasets | 189 |
| abstract_inverted_index.decouple | 82 |
| abstract_inverted_index.distinct | 116 |
| abstract_inverted_index.enabling | 146 |
| abstract_inverted_index.identify | 167 |
| abstract_inverted_index.includes | 77 |
| abstract_inverted_index.involves | 64 |
| abstract_inverted_index.learning | 10, 36, 186 |
| abstract_inverted_index.networks | 88, 118 |
| abstract_inverted_index.observed | 38 |
| abstract_inverted_index.optimize | 115 |
| abstract_inverted_index.parallel | 156 |
| abstract_inverted_index.released | 198 |
| abstract_inverted_index.research | 48 |
| abstract_inverted_index.speed-up | 149 |
| abstract_inverted_index.updating | 27, 128 |
| abstract_inverted_index.approach: | 102 |
| abstract_inverted_index.auxiliary | 87 |
| abstract_inverted_index.backward- | 17 |
| abstract_inverted_index.decisions | 78 |
| abstract_inverted_index.decoupled | 169 |
| abstract_inverted_index.determine | 69 |
| abstract_inverted_index.extensive | 65 |
| abstract_inverted_index.introduce | 98 |
| abstract_inverted_index.leverages | 110 |
| abstract_inverted_index.parallel, | 145 |
| abstract_inverted_index.potential | 148 |
| abstract_inverted_index.processes | 37 |
| abstract_inverted_index.suggested | 50 |
| abstract_inverted_index.technique | 7 |
| abstract_inverted_index.training. | 75 |
| abstract_inverted_index.biological | 22 |
| abstract_inverted_index.block-wise | 104, 185 |
| abstract_inverted_index.concurrent | 26 |
| abstract_inverted_index.end-to-end | 180 |
| abstract_inverted_index.iterations | 67 |
| abstract_inverted_index.sub-neural | 117 |
| abstract_inverted_index.successful | 5 |
| abstract_inverted_index.techniques | 187 |
| abstract_inverted_index.responsible | 126 |
| abstract_inverted_index.separately, | 119 |
| abstract_inverted_index.variations, | 175 |
| abstract_inverted_index.consistently | 161 |
| abstract_inverted_index.experimental | 159 |
| abstract_inverted_index.limitations, | 14 |
| abstract_inverted_index.optimization | 6 |
| abstract_inverted_index.transferable | 168 |
| abstract_inverted_index.architectures | 170 |
| abstract_inverted_index.configuration | 72 |
| abstract_inverted_index.outperforming | 176 |
| abstract_inverted_index.Tiny-ImageNet. | 194 |
| abstract_inverted_index.asynchronously | 56 |
| abstract_inverted_index.Backpropagation | 0 |
| abstract_inverted_index.backpropagation | 181 |
| abstract_inverted_index.implausibility, | 23 |
| abstract_inverted_index.implementation. | 157 |
| abstract_inverted_index.trial-and-error | 66 |
| abstract_inverted_index.update-locking, | 19 |
| abstract_inverted_index.state-of-the-art | 184 |
| abstract_inverted_index.https://github.com/Belis0811/BWBPF. | 200 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |