Testing the Channels of Convolutional Neural Networks Article Swipe
Kang Choi
,
Donghyun Son
,
Young-Hoon Kim
,
Jiwon Seo
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2303.03400
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2303.03400
Neural networks have complex structures, and thus it is hard to understand their inner workings and ensure correctness. To understand and debug convolutional neural networks (CNNs) we propose techniques for testing the channels of CNNs. We design FtGAN, an extension to GAN, that can generate test data with varying the intensity (i.e., sum of the neurons) of a channel of a target CNN. We also proposed a channel selection algorithm to find representative channels for testing. To efficiently inspect the target CNN's inference computations, we define unexpectedness score, which estimates how similar the inference computation of the test data is to that of the training data. We evaluated FtGAN with five public datasets and showed that our techniques successfully identify defective channels in five different CNN models.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2303.03400
- https://arxiv.org/pdf/2303.03400
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4323650258
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4323650258Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2303.03400Digital Object Identifier
- Title
-
Testing the Channels of Convolutional Neural NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-03-06Full publication date if available
- Authors
-
Kang Choi, Donghyun Son, Young-Hoon Kim, Jiwon SeoList of authors in order
- Landing page
-
https://arxiv.org/abs/2303.03400Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2303.03400Direct 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/2303.03400Direct OA link when available
- Concepts
-
Convolutional neural network, Correctness, Inference, Computer science, Computation, Channel (broadcasting), Debugging, Artificial intelligence, Pattern recognition (psychology), Machine learning, Algorithm, Computer network, Programming languageTop 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/W4323650258 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2303.03400 |
| ids.doi | https://doi.org/10.48550/arxiv.2303.03400 |
| ids.openalex | https://openalex.org/W4323650258 |
| fwci | |
| type | preprint |
| title | Testing the Channels of Convolutional Neural Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T11689 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9990000128746033 |
| 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 | Adversarial Robustness in Machine Learning |
| topics[1].id | https://openalex.org/T12026 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9829000234603882 |
| topics[1].domain.id | https://openalex.org/domains/3 |
| topics[1].domain.display_name | Physical Sciences |
| topics[1].subfield.id | https://openalex.org/subfields/1702 |
| topics[1].subfield.display_name | Artificial Intelligence |
| topics[1].display_name | Explainable Artificial Intelligence (XAI) |
| topics[2].id | https://openalex.org/T11512 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.98089998960495 |
| 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 | Anomaly Detection Techniques and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C81363708 |
| concepts[0].level | 2 |
| concepts[0].score | 0.8444979190826416 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[0].display_name | Convolutional neural network |
| concepts[1].id | https://openalex.org/C55439883 |
| concepts[1].level | 2 |
| concepts[1].score | 0.7439651489257812 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q360812 |
| concepts[1].display_name | Correctness |
| concepts[2].id | https://openalex.org/C2776214188 |
| concepts[2].level | 2 |
| concepts[2].score | 0.7388225793838501 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q408386 |
| concepts[2].display_name | Inference |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.7299431562423706 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C45374587 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6637653708457947 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q12525525 |
| concepts[4].display_name | Computation |
| concepts[5].id | https://openalex.org/C127162648 |
| concepts[5].level | 2 |
| concepts[5].score | 0.6203047037124634 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q16858953 |
| concepts[5].display_name | Channel (broadcasting) |
| concepts[6].id | https://openalex.org/C168065819 |
| concepts[6].level | 2 |
| concepts[6].score | 0.49579057097435 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q845566 |
| concepts[6].display_name | Debugging |
| concepts[7].id | https://openalex.org/C154945302 |
| concepts[7].level | 1 |
| concepts[7].score | 0.49233925342559814 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[7].display_name | Artificial intelligence |
| concepts[8].id | https://openalex.org/C153180895 |
| concepts[8].level | 2 |
| concepts[8].score | 0.3769630789756775 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[8].display_name | Pattern recognition (psychology) |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.36235684156417847 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C11413529 |
| concepts[10].level | 1 |
| concepts[10].score | 0.3152604401111603 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q8366 |
| concepts[10].display_name | Algorithm |
| concepts[11].id | https://openalex.org/C31258907 |
| concepts[11].level | 1 |
| concepts[11].score | 0.085002601146698 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q1301371 |
| concepts[11].display_name | Computer network |
| 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 |
| keywords[0].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[0].score | 0.8444979190826416 |
| keywords[0].display_name | Convolutional neural network |
| keywords[1].id | https://openalex.org/keywords/correctness |
| keywords[1].score | 0.7439651489257812 |
| keywords[1].display_name | Correctness |
| keywords[2].id | https://openalex.org/keywords/inference |
| keywords[2].score | 0.7388225793838501 |
| keywords[2].display_name | Inference |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.7299431562423706 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/computation |
| keywords[4].score | 0.6637653708457947 |
| keywords[4].display_name | Computation |
| keywords[5].id | https://openalex.org/keywords/channel |
| keywords[5].score | 0.6203047037124634 |
| keywords[5].display_name | Channel (broadcasting) |
| keywords[6].id | https://openalex.org/keywords/debugging |
| keywords[6].score | 0.49579057097435 |
| keywords[6].display_name | Debugging |
| keywords[7].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[7].score | 0.49233925342559814 |
| keywords[7].display_name | Artificial intelligence |
| keywords[8].id | https://openalex.org/keywords/pattern-recognition |
| keywords[8].score | 0.3769630789756775 |
| keywords[8].display_name | Pattern recognition (psychology) |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.36235684156417847 |
| keywords[9].display_name | Machine learning |
| keywords[10].id | https://openalex.org/keywords/algorithm |
| keywords[10].score | 0.3152604401111603 |
| keywords[10].display_name | Algorithm |
| keywords[11].id | https://openalex.org/keywords/computer-network |
| keywords[11].score | 0.085002601146698 |
| keywords[11].display_name | Computer network |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2303.03400 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | https://arxiv.org/pdf/2303.03400 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2303.03400 |
| locations[1].id | doi:10.48550/arxiv.2303.03400 |
| 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.2303.03400 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5109336063 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Kang Choi |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Choi, Kang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5057983260 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Donghyun Son |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Son, Donghyun |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5100327659 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-0265-3825 |
| authorships[2].author.display_name | Young-Hoon Kim |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Kim, Younghoon |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100657256 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-1781-533X |
| authorships[3].author.display_name | Jiwon Seo |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Seo, Jiwon |
| authorships[3].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://arxiv.org/pdf/2303.03400 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Testing the Channels of Convolutional Neural Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T11689 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9990000128746033 |
| 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 | Adversarial Robustness in Machine Learning |
| related_works | https://openalex.org/W1667647204, https://openalex.org/W2404647514, https://openalex.org/W4247536566, https://openalex.org/W4321442002, https://openalex.org/W2018477250, https://openalex.org/W3119814709, https://openalex.org/W4241418540, https://openalex.org/W1508895727, https://openalex.org/W2015265939, https://openalex.org/W1524101012 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2303.03400 |
| 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/2303.03400 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| 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/2303.03400 |
| primary_location.id | pmh:oai:arXiv.org:2303.03400 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | https://arxiv.org/pdf/2303.03400 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2303.03400 |
| publication_date | 2023-03-06 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 57, 60, 66 |
| abstract_inverted_index.To | 18, 76 |
| abstract_inverted_index.We | 35, 63, 106 |
| abstract_inverted_index.an | 38 |
| abstract_inverted_index.in | 122 |
| abstract_inverted_index.is | 8, 99 |
| abstract_inverted_index.it | 7 |
| abstract_inverted_index.of | 33, 53, 56, 59, 95, 102 |
| abstract_inverted_index.to | 10, 40, 70, 100 |
| abstract_inverted_index.we | 26, 84 |
| abstract_inverted_index.CNN | 125 |
| abstract_inverted_index.and | 5, 15, 20, 113 |
| abstract_inverted_index.can | 43 |
| abstract_inverted_index.for | 29, 74 |
| abstract_inverted_index.how | 90 |
| abstract_inverted_index.our | 116 |
| abstract_inverted_index.sum | 52 |
| abstract_inverted_index.the | 31, 49, 54, 79, 92, 96, 103 |
| abstract_inverted_index.CNN. | 62 |
| abstract_inverted_index.GAN, | 41 |
| abstract_inverted_index.also | 64 |
| abstract_inverted_index.data | 46, 98 |
| abstract_inverted_index.find | 71 |
| abstract_inverted_index.five | 110, 123 |
| abstract_inverted_index.hard | 9 |
| abstract_inverted_index.have | 2 |
| abstract_inverted_index.test | 45, 97 |
| abstract_inverted_index.that | 42, 101, 115 |
| abstract_inverted_index.thus | 6 |
| abstract_inverted_index.with | 47, 109 |
| abstract_inverted_index.CNN's | 81 |
| abstract_inverted_index.CNNs. | 34 |
| abstract_inverted_index.FtGAN | 108 |
| abstract_inverted_index.data. | 105 |
| abstract_inverted_index.debug | 21 |
| abstract_inverted_index.inner | 13 |
| abstract_inverted_index.their | 12 |
| abstract_inverted_index.which | 88 |
| abstract_inverted_index.(CNNs) | 25 |
| abstract_inverted_index.(i.e., | 51 |
| abstract_inverted_index.FtGAN, | 37 |
| abstract_inverted_index.Neural | 0 |
| abstract_inverted_index.define | 85 |
| abstract_inverted_index.design | 36 |
| abstract_inverted_index.ensure | 16 |
| abstract_inverted_index.neural | 23 |
| abstract_inverted_index.public | 111 |
| abstract_inverted_index.score, | 87 |
| abstract_inverted_index.showed | 114 |
| abstract_inverted_index.target | 61, 80 |
| abstract_inverted_index.channel | 58, 67 |
| abstract_inverted_index.complex | 3 |
| abstract_inverted_index.inspect | 78 |
| abstract_inverted_index.models. | 126 |
| abstract_inverted_index.propose | 27 |
| abstract_inverted_index.similar | 91 |
| abstract_inverted_index.testing | 30 |
| abstract_inverted_index.varying | 48 |
| abstract_inverted_index.channels | 32, 73, 121 |
| abstract_inverted_index.datasets | 112 |
| abstract_inverted_index.generate | 44 |
| abstract_inverted_index.identify | 119 |
| abstract_inverted_index.networks | 1, 24 |
| abstract_inverted_index.neurons) | 55 |
| abstract_inverted_index.proposed | 65 |
| abstract_inverted_index.testing. | 75 |
| abstract_inverted_index.training | 104 |
| abstract_inverted_index.workings | 14 |
| abstract_inverted_index.algorithm | 69 |
| abstract_inverted_index.defective | 120 |
| abstract_inverted_index.different | 124 |
| abstract_inverted_index.estimates | 89 |
| abstract_inverted_index.evaluated | 107 |
| abstract_inverted_index.extension | 39 |
| abstract_inverted_index.inference | 82, 93 |
| abstract_inverted_index.intensity | 50 |
| abstract_inverted_index.selection | 68 |
| abstract_inverted_index.techniques | 28, 117 |
| abstract_inverted_index.understand | 11, 19 |
| abstract_inverted_index.computation | 94 |
| abstract_inverted_index.efficiently | 77 |
| abstract_inverted_index.structures, | 4 |
| abstract_inverted_index.correctness. | 17 |
| abstract_inverted_index.successfully | 118 |
| abstract_inverted_index.computations, | 83 |
| abstract_inverted_index.convolutional | 22 |
| abstract_inverted_index.representative | 72 |
| abstract_inverted_index.unexpectedness | 86 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |