Unit Impulse Response as an Explainer of Redundancy in a Deep Convolutional Neural Network Article Swipe
Convolutional neural networks (CNN) are generally designed with a heuristic initialization of network architecture and trained for a certain task. This often leads to overparametrization after learning and induces redundancy in the information flow paths within the network. This robustness and reliability is at the increased cost of redundant computations. Several methods have been proposed which leverage metrics that quantify the redundancy in each layer. However, layer-wise evaluation in these methods disregards the long-range redundancy which exists across depth on account of the distributed nature of the features learned by the model. In this paper, we propose (i) a mechanism to empirically demonstrate the robustness in performance of a CNN on account of redundancy across its depth, (ii) a method to identify the systemic redundancy in response of a CNN across depth using the understanding of unit impulse response, we subsequently demonstrate use of these methods to interpret redundancy in few networks as example. These techniques provide better insights into the internal dynamics of a CNN
Related Topics
Concepts
Metadata
- Type
- article
- Language
- en
- Landing Page
- https://arxiv.org/pdf/1906.03986.pdf
- OA Status
- green
- Related Works
- 20
- OpenAlex ID
- https://openalex.org/W2969054201
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W2969054201Canonical identifier for this work in OpenAlex
- Title
-
Unit Impulse Response as an Explainer of Redundancy in a Deep Convolutional Neural NetworkWork title
- Type
-
articleOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2019Year of publication
- Publication date
-
2019-01-01Full publication date if available
- Authors
-
Rachana Sathish, Debdoot SheetList of authors in order
- Landing page
-
https://arxiv.org/pdf/1906.03986.pdfPublisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/1906.03986.pdfDirect OA link when available
- Concepts
-
Computer science, Redundancy (engineering), Convolutional neural network, Robustness (evolution), Artificial intelligence, Initialization, Artificial neural network, Biochemistry, Chemistry, Operating system, Programming language, GeneTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
20Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W2969054201 |
|---|---|
| doi | |
| ids.mag | 2969054201 |
| ids.openalex | https://openalex.org/W2969054201 |
| fwci | 0.0 |
| type | article |
| title | Unit Impulse Response as an Explainer of Redundancy in a Deep Convolutional Neural Network |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | 27 |
| biblio.first_page | 24 |
| topics[0].id | https://openalex.org/T11512 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9847000241279602 |
| 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 | Anomaly Detection Techniques and Applications |
| topics[1].id | https://openalex.org/T10320 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9714999794960022 |
| 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 | Neural Networks and Applications |
| topics[2].id | https://openalex.org/T11689 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9688000082969666 |
| 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 | Adversarial Robustness in Machine Learning |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.7993751764297485 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C152124472 |
| concepts[1].level | 2 |
| concepts[1].score | 0.6876627802848816 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q1204361 |
| concepts[1].display_name | Redundancy (engineering) |
| concepts[2].id | https://openalex.org/C81363708 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6747155785560608 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q17084460 |
| concepts[2].display_name | Convolutional neural network |
| concepts[3].id | https://openalex.org/C63479239 |
| concepts[3].level | 3 |
| concepts[3].score | 0.4915564954280853 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[3].display_name | Robustness (evolution) |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.48609113693237305 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C114466953 |
| concepts[5].level | 2 |
| concepts[5].score | 0.4714813232421875 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q6034165 |
| concepts[5].display_name | Initialization |
| concepts[6].id | https://openalex.org/C50644808 |
| concepts[6].level | 2 |
| concepts[6].score | 0.41178661584854126 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[6].display_name | Artificial neural network |
| concepts[7].id | https://openalex.org/C55493867 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[7].display_name | Biochemistry |
| concepts[8].id | https://openalex.org/C185592680 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[8].display_name | Chemistry |
| concepts[9].id | https://openalex.org/C111919701 |
| concepts[9].level | 1 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[9].display_name | Operating system |
| concepts[10].id | https://openalex.org/C199360897 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[10].display_name | Programming language |
| concepts[11].id | https://openalex.org/C104317684 |
| concepts[11].level | 2 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[11].display_name | Gene |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.7993751764297485 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/redundancy |
| keywords[1].score | 0.6876627802848816 |
| keywords[1].display_name | Redundancy (engineering) |
| keywords[2].id | https://openalex.org/keywords/convolutional-neural-network |
| keywords[2].score | 0.6747155785560608 |
| keywords[2].display_name | Convolutional neural network |
| keywords[3].id | https://openalex.org/keywords/robustness |
| keywords[3].score | 0.4915564954280853 |
| keywords[3].display_name | Robustness (evolution) |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.48609113693237305 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/initialization |
| keywords[5].score | 0.4714813232421875 |
| keywords[5].display_name | Initialization |
| keywords[6].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[6].score | 0.41178661584854126 |
| keywords[6].display_name | Artificial neural network |
| language | en |
| locations[0].id | mag:2969054201 |
| 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 | |
| locations[0].version | |
| locations[0].raw_type | |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | |
| locations[0].raw_source_name | arXiv (Cornell University) |
| locations[0].landing_page_url | https://arxiv.org/pdf/1906.03986.pdf |
| authorships[0].author.id | https://openalex.org/A5102806062 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-3402-3852 |
| authorships[0].author.display_name | Rachana Sathish |
| authorships[0].countries | IN |
| authorships[0].affiliations[0].institution_ids | https://openalex.org/I145894827 |
| authorships[0].affiliations[0].raw_affiliation_string | Indian Institute of Technology Kharagpur, Kharagpur, India |
| authorships[0].institutions[0].id | https://openalex.org/I145894827 |
| authorships[0].institutions[0].ror | https://ror.org/03w5sq511 |
| authorships[0].institutions[0].type | education |
| authorships[0].institutions[0].lineage | https://openalex.org/I145894827 |
| authorships[0].institutions[0].country_code | IN |
| authorships[0].institutions[0].display_name | Indian Institute of Technology Kharagpur |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Rachana Sathish |
| authorships[0].is_corresponding | False |
| authorships[0].raw_affiliation_strings | Indian Institute of Technology Kharagpur, Kharagpur, India |
| authorships[1].author.id | https://openalex.org/A5010986022 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9046-149X |
| authorships[1].author.display_name | Debdoot Sheet |
| authorships[1].countries | IN |
| authorships[1].affiliations[0].institution_ids | https://openalex.org/I145894827 |
| authorships[1].affiliations[0].raw_affiliation_string | Indian Institute of Technology Kharagpur, Kharagpur, India |
| authorships[1].institutions[0].id | https://openalex.org/I145894827 |
| authorships[1].institutions[0].ror | https://ror.org/03w5sq511 |
| authorships[1].institutions[0].type | education |
| authorships[1].institutions[0].lineage | https://openalex.org/I145894827 |
| authorships[1].institutions[0].country_code | IN |
| authorships[1].institutions[0].display_name | Indian Institute of Technology Kharagpur |
| authorships[1].author_position | last |
| authorships[1].raw_author_name | Debdoot Sheet |
| authorships[1].is_corresponding | False |
| authorships[1].raw_affiliation_strings | Indian Institute of Technology Kharagpur, Kharagpur, India |
| 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/1906.03986.pdf |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Unit Impulse Response as an Explainer of Redundancy in a Deep Convolutional Neural Network |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-10-10T17:16:08.811792 |
| primary_topic.id | https://openalex.org/T11512 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9847000241279602 |
| 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 | Anomaly Detection Techniques and Applications |
| related_works | https://openalex.org/W2948039667, https://openalex.org/W3010204512, https://openalex.org/W2896126933, https://openalex.org/W3097334049, https://openalex.org/W3164947374, https://openalex.org/W3163875631, https://openalex.org/W2166548692, https://openalex.org/W2811297269, https://openalex.org/W3208750921, https://openalex.org/W3023750926, https://openalex.org/W3095146057, https://openalex.org/W1527646298, https://openalex.org/W3094157122, https://openalex.org/W2903143476, https://openalex.org/W3098989436, https://openalex.org/W2967141048, https://openalex.org/W2747977736, https://openalex.org/W3180849877, https://openalex.org/W2964113612, https://openalex.org/W2894304603 |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | mag:2969054201 |
| 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 | |
| best_oa_location.version | |
| best_oa_location.raw_type | |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | arXiv (Cornell University) |
| best_oa_location.landing_page_url | https://arxiv.org/pdf/1906.03986.pdf |
| primary_location.id | mag:2969054201 |
| 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 | |
| primary_location.version | |
| primary_location.raw_type | |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | arXiv (Cornell University) |
| primary_location.landing_page_url | https://arxiv.org/pdf/1906.03986.pdf |
| publication_date | 2019-01-01 |
| publication_year | 2019 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 8, 17, 98, 108, 118, 128, 164 |
| abstract_inverted_index.In | 92 |
| abstract_inverted_index.as | 152 |
| abstract_inverted_index.at | 43 |
| abstract_inverted_index.by | 89 |
| abstract_inverted_index.in | 30, 62, 68, 105, 125, 149 |
| abstract_inverted_index.is | 42 |
| abstract_inverted_index.of | 11, 47, 81, 85, 107, 112, 127, 135, 143, 163 |
| abstract_inverted_index.on | 79, 110 |
| abstract_inverted_index.to | 23, 100, 120, 146 |
| abstract_inverted_index.we | 95, 139 |
| abstract_inverted_index.(i) | 97 |
| abstract_inverted_index.CNN | 109, 129, 165 |
| abstract_inverted_index.and | 14, 27, 40 |
| abstract_inverted_index.are | 4 |
| abstract_inverted_index.few | 150 |
| abstract_inverted_index.for | 16 |
| abstract_inverted_index.its | 115 |
| abstract_inverted_index.the | 31, 36, 44, 60, 72, 82, 86, 90, 103, 122, 133, 160 |
| abstract_inverted_index.use | 142 |
| abstract_inverted_index.(ii) | 117 |
| abstract_inverted_index.This | 20, 38 |
| abstract_inverted_index.been | 53 |
| abstract_inverted_index.cost | 46 |
| abstract_inverted_index.each | 63 |
| abstract_inverted_index.flow | 33 |
| abstract_inverted_index.have | 52 |
| abstract_inverted_index.into | 159 |
| abstract_inverted_index.that | 58 |
| abstract_inverted_index.this | 93 |
| abstract_inverted_index.unit | 136 |
| abstract_inverted_index.with | 7 |
| abstract_inverted_index.(CNN) | 3 |
| abstract_inverted_index.These | 154 |
| abstract_inverted_index.after | 25 |
| abstract_inverted_index.depth | 78, 131 |
| abstract_inverted_index.leads | 22 |
| abstract_inverted_index.often | 21 |
| abstract_inverted_index.paths | 34 |
| abstract_inverted_index.task. | 19 |
| abstract_inverted_index.these | 69, 144 |
| abstract_inverted_index.using | 132 |
| abstract_inverted_index.which | 55, 75 |
| abstract_inverted_index.across | 77, 114, 130 |
| abstract_inverted_index.better | 157 |
| abstract_inverted_index.depth, | 116 |
| abstract_inverted_index.exists | 76 |
| abstract_inverted_index.layer. | 64 |
| abstract_inverted_index.method | 119 |
| abstract_inverted_index.model. | 91 |
| abstract_inverted_index.nature | 84 |
| abstract_inverted_index.neural | 1 |
| abstract_inverted_index.paper, | 94 |
| abstract_inverted_index.within | 35 |
| abstract_inverted_index.Several | 50 |
| abstract_inverted_index.account | 80, 111 |
| abstract_inverted_index.certain | 18 |
| abstract_inverted_index.impulse | 137 |
| abstract_inverted_index.induces | 28 |
| abstract_inverted_index.learned | 88 |
| abstract_inverted_index.methods | 51, 70, 145 |
| abstract_inverted_index.metrics | 57 |
| abstract_inverted_index.network | 12 |
| abstract_inverted_index.propose | 96 |
| abstract_inverted_index.provide | 156 |
| abstract_inverted_index.trained | 15 |
| abstract_inverted_index.However, | 65 |
| abstract_inverted_index.designed | 6 |
| abstract_inverted_index.dynamics | 162 |
| abstract_inverted_index.example. | 153 |
| abstract_inverted_index.features | 87 |
| abstract_inverted_index.identify | 121 |
| abstract_inverted_index.insights | 158 |
| abstract_inverted_index.internal | 161 |
| abstract_inverted_index.learning | 26 |
| abstract_inverted_index.leverage | 56 |
| abstract_inverted_index.network. | 37 |
| abstract_inverted_index.networks | 2, 151 |
| abstract_inverted_index.proposed | 54 |
| abstract_inverted_index.quantify | 59 |
| abstract_inverted_index.response | 126 |
| abstract_inverted_index.systemic | 123 |
| abstract_inverted_index.generally | 5 |
| abstract_inverted_index.heuristic | 9 |
| abstract_inverted_index.increased | 45 |
| abstract_inverted_index.interpret | 147 |
| abstract_inverted_index.mechanism | 99 |
| abstract_inverted_index.redundant | 48 |
| abstract_inverted_index.response, | 138 |
| abstract_inverted_index.disregards | 71 |
| abstract_inverted_index.evaluation | 67 |
| abstract_inverted_index.layer-wise | 66 |
| abstract_inverted_index.long-range | 73 |
| abstract_inverted_index.redundancy | 29, 61, 74, 113, 124, 148 |
| abstract_inverted_index.robustness | 39, 104 |
| abstract_inverted_index.techniques | 155 |
| abstract_inverted_index.demonstrate | 102, 141 |
| abstract_inverted_index.distributed | 83 |
| abstract_inverted_index.empirically | 101 |
| abstract_inverted_index.information | 32 |
| abstract_inverted_index.performance | 106 |
| abstract_inverted_index.reliability | 41 |
| abstract_inverted_index.architecture | 13 |
| abstract_inverted_index.subsequently | 140 |
| abstract_inverted_index.Convolutional | 0 |
| abstract_inverted_index.computations. | 49 |
| abstract_inverted_index.understanding | 134 |
| abstract_inverted_index.initialization | 10 |
| abstract_inverted_index.overparametrization | 24 |
| cited_by_percentile_year | |
| countries_distinct_count | 1 |
| institutions_distinct_count | 2 |
| citation_normalized_percentile.value | 0.08800628 |
| citation_normalized_percentile.is_in_top_1_percent | False |
| citation_normalized_percentile.is_in_top_10_percent | False |