Adaptive Growth: Real-time CNN Layer Expansion
Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This research presents a new algorithm that allows the convolutiona...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
30.09.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This research presents a new algorithm that allows the convolutional layer of a Convolutional Neural Network (CNN) to dynamically evolve based on data input, while still being seamlessly integrated into existing DNNs. Instead of a rigid architecture, our approach iteratively introduces kernels to the convolutional layer, gauging its real-time response to varying data. This process is refined by evaluating the layer's capacity to discern image features, guiding its growth. Remarkably, our unsupervised method has outstripped its supervised counterparts across diverse datasets like MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. It also showcases enhanced adaptability in transfer learning scenarios. By introducing a data-driven model scalability strategy, we are filling a void in deep learning, leading to more flexible and efficient DNNs suited for dynamic settings. Code:(https://github.com/YunjieZhu/Extensible-Convolutional-Layer-git-version). |
---|---|
AbstractList | Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their static structure limits their adaptability in ever-changing environments. This research presents a new algorithm that allows the convolutional layer of a Convolutional Neural Network (CNN) to dynamically evolve based on data input, while still being seamlessly integrated into existing DNNs. Instead of a rigid architecture, our approach iteratively introduces kernels to the convolutional layer, gauging its real-time response to varying data. This process is refined by evaluating the layer's capacity to discern image features, guiding its growth. Remarkably, our unsupervised method has outstripped its supervised counterparts across diverse datasets like MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100. It also showcases enhanced adaptability in transfer learning scenarios. By introducing a data-driven model scalability strategy, we are filling a void in deep learning, leading to more flexible and efficient DNNs suited for dynamic settings. Code:(https://github.com/YunjieZhu/Extensible-Convolutional-Layer-git-version). |
Author | Chen, Yunhao Zhu, Yunjie |
Author_xml | – sequence: 1 givenname: Yunjie surname: Zhu fullname: Zhu, Yunjie – sequence: 2 givenname: Yunhao surname: Chen fullname: Chen, Yunhao |
BookMark | eNrjYmDJy89LZWLgNDI2NtS1MDEy4mDgLS7OMjAwMDIzNzI1NeZk0HNMSSwoySxLVXAvyi8vybBSCEpNzNEtycxNVXD281PwSaxMLVJwrShIzCvOzM_jYWBNS8wpTuWF0twMym6uIc4eugVF-YWlqcUl8Vn5pUV5QKl4IwszQ0tLE0sDS2PiVAEAvs0zVw |
ContentType | Paper |
Copyright | 2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_28619949093 |
IEDL.DBID | BENPR |
IngestDate | Wed Sep 25 00:28:54 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_28619949093 |
OpenAccessLink | https://www.proquest.com/docview/2861994909/abstract/?pq-origsite=%requestingapplication% |
PQID | 2861994909 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2861994909 |
PublicationCentury | 2000 |
PublicationDate | 20230930 |
PublicationDateYYYYMMDD | 2023-09-30 |
PublicationDate_xml | – month: 09 year: 2023 text: 20230930 day: 30 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2023 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.4894972 |
SecondaryResourceType | preprint |
Snippet | Deep Neural Networks (DNNs) have shown unparalleled achievements in numerous applications, reflecting their proficiency in managing vast data sets. Yet, their... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Algorithms Artificial neural networks Changing environments Deep learning Machine learning Neural networks Real time Time response |
Title | Adaptive Growth: Real-time CNN Layer Expansion |
URI | https://www.proquest.com/docview/2861994909/abstract/ |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1LS8QwEB52twjefOJjXQJ6ja1t0ocX0aXdIlqWRWFvS5JGPLl1t4Inf7sztdWDsMcQSMiQeXwzk3wAFyaJPBOVAVex0lxI6XNViognQakDqT2BAI66LYowfxb3cznvQd69haG2ys4mNoa6XBrKkbt-HNI3tomXuEpTFsDU7k31zok_iuqsLZlGHxz_SlDB1rlLi-nsN9_ihxFGz8E_k9v4kWwHnKmq7GoXevZtD7aa9kuz3ofL21JVZHjYBGFx_XrNZhjAcSJ-Z-OiYA8KI2OWfqLqUnbrAM6z9Gmc826TRXsl1ou_AwSHMEBsb4-A2VgbREBSo7iE9uIEJeYbq6R5MagP-hiGm1Y62Tx9CtvEjv7T3jCEQb36sGfoQ2s9gn6cTUatkHD0-JV-Axcae_g |
link.rule.ids | 786,790,12792,21416,33408,33779,43635,43840 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV1NS8QwEB20RfTmJ36sGtBrtDRJP7yILl2r1rIsK-ytJGnEk9ZtBX--k5rVg7DnQBKG5M28l0cG4FyncaDjmlGZSEW5ECGVNY9pymrFhAo4Ejjrtiij_Jk_zMTMCW6ts1UuMLEH6vpdW438Mkwi-41tGqTXzQe1XaPs66probEKPmdIVTzwb7NyPPlVWcIoxpqZ_QPaPnuMNsEfy8bMt2DFvG3DWm-61O0OXNzUsrFwQ-6QDHevV2SCZRu17d7JsCxJIbEeJtkXXlirae3C2SibDnO6WKRyB6Gt_rbN9sBDRm_2gZhEaeQ9QmGQuAqSFOMUaiOFftF4C9QBDJbNdLh8-BTW8-lTURX35eMRbNj-6D8GhwF43fzTHGMW7dSJC9U3Koh5FA |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Adaptive+Growth%3A+Real-time+CNN+Layer+Expansion&rft.jtitle=arXiv.org&rft.au=Zhu%2C+Yunjie&rft.au=Chen%2C+Yunhao&rft.date=2023-09-30&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |