Performance of basic networks trained on shape-only images.
<p>Accuracy of basic networks after training on 18 × 18-pixel shape-only image datasets. Error bars indicate 95% confidence intervals estimated from 10 training runs with different random initial weights. Stars indicate that accuracy is significantly above chance level (horizontal line) accord...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | |
| منشور في: |
2024
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852025273268043776 |
|---|---|
| author | Christian Jarvers (6328562) |
| author2 | Heiko Neumann (106738) |
| author2_role | author |
| author_facet | Christian Jarvers (6328562) Heiko Neumann (106738) |
| author_role | author |
| dc.creator.none.fl_str_mv | Christian Jarvers (6328562) Heiko Neumann (106738) |
| dc.date.none.fl_str_mv | 2024-11-11T18:44:28Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pcbi.1012019.g005 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Performance_of_basic_networks_trained_on_shape-only_images_/27658614 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified different learning algorithms batch gradient descent whereas humans base primate visual system local weight changes artificial image datasets teaching deep networks one crucial problem use shape features whereas others weight updates use shape primate vision image class training networks make networks widely documented strong shape single features see shape remarkably successful network architectures many images large extent feature combinations design simple classify images category membership biased towards |
| dc.title.none.fl_str_mv | Performance of basic networks trained on shape-only images. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <p>Accuracy of basic networks after training on 18 × 18-pixel shape-only image datasets. Error bars indicate 95% confidence intervals estimated from 10 training runs with different random initial weights. Stars indicate that accuracy is significantly above chance level (horizontal line) according to a sign test. Circles indicate that accuracy is significantly below chance level.</p> |
| eu_rights_str_mv | openAccess |
| id | Manara_7c668dca9af2bb53d8fc32ae229e0622 |
| identifier_str_mv | 10.1371/journal.pcbi.1012019.g005 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/27658614 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Performance of basic networks trained on shape-only images.Christian Jarvers (6328562)Heiko Neumann (106738)Science PolicyBiological Sciences not elsewhere classifiedInformation Systems not elsewhere classifieddifferent learning algorithmsbatch gradient descentwhereas humans baseprimate visual systemlocal weight changesartificial image datasetsteaching deep networksone crucial problemuse shape featureswhereas othersweight updatesuse shapeprimate visionimage classtraining networksmake networkswidely documentedstrong shapesingle featuressee shaperemarkably successfulnetwork architecturesmany imageslarge extentfeature combinationsdesign simpleclassify imagescategory membershipbiased towards<p>Accuracy of basic networks after training on 18 × 18-pixel shape-only image datasets. Error bars indicate 95% confidence intervals estimated from 10 training runs with different random initial weights. Stars indicate that accuracy is significantly above chance level (horizontal line) according to a sign test. Circles indicate that accuracy is significantly below chance level.</p>2024-11-11T18:44:28ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pcbi.1012019.g005https://figshare.com/articles/figure/Performance_of_basic_networks_trained_on_shape-only_images_/27658614CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/276586142024-11-11T18:44:28Z |
| spellingShingle | Performance of basic networks trained on shape-only images. Christian Jarvers (6328562) Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified different learning algorithms batch gradient descent whereas humans base primate visual system local weight changes artificial image datasets teaching deep networks one crucial problem use shape features whereas others weight updates use shape primate vision image class training networks make networks widely documented strong shape single features see shape remarkably successful network architectures many images large extent feature combinations design simple classify images category membership biased towards |
| status_str | publishedVersion |
| title | Performance of basic networks trained on shape-only images. |
| title_full | Performance of basic networks trained on shape-only images. |
| title_fullStr | Performance of basic networks trained on shape-only images. |
| title_full_unstemmed | Performance of basic networks trained on shape-only images. |
| title_short | Performance of basic networks trained on shape-only images. |
| title_sort | Performance of basic networks trained on shape-only images. |
| topic | Science Policy Biological Sciences not elsewhere classified Information Systems not elsewhere classified different learning algorithms batch gradient descent whereas humans base primate visual system local weight changes artificial image datasets teaching deep networks one crucial problem use shape features whereas others weight updates use shape primate vision image class training networks make networks widely documented strong shape single features see shape remarkably successful network architectures many images large extent feature combinations design simple classify images category membership biased towards |