Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lim, Heechul | - |
dc.contributor.author | Kim, Min-Soo | - |
dc.date.accessioned | 2022-11-10T12:10:10Z | - |
dc.date.available | 2022-11-10T12:10:10Z | - |
dc.date.created | 2022-08-25 | - |
dc.date.issued | 2022-08 | - |
dc.identifier.issn | 2169-3536 | - |
dc.identifier.uri | http://hdl.handle.net/20.500.11750/17096 | - |
dc.description.abstract | There is growing interest in automating designing good neural network architectures. The NAS methods proposed recently have significantly reduced the architecture search cost by sharing parameters, but there is still a challenging problem in designing search space. The existing operation-level architecture search methods require a large amount of computing power or designing the search space of operations very carefully. In this paper, we investigate the possibility of achieving competitive performance with them only using a small amount of computing power and without designing search space carefully. We propose TENAS using Taylor expansion and only a fixed type of operation. The resulting architecture is sparse in terms of channel and has different topology at different cells. The experimental results for CIFAR-10 and ImageNet show that a fine-granular and sparse model searched by TENAS achieves very competitive performance with dense models searched by the existing methods. Author | - |
dc.language | English | - |
dc.publisher | Institute of Electrical and Electronics Engineers Inc. | - |
dc.title | TENAS: Using Taylor Expansion and Channel-level Skip Connection for Neural Architecture Search | - |
dc.type | Article | - |
dc.identifier.doi | 10.1109/ACCESS.2022.3195208 | - |
dc.identifier.scopusid | 2-s2.0-85135747464 | - |
dc.identifier.bibliographicCitation | IEEE Access, v.10, pp.84790 - 84798 | - |
dc.description.isOpenAccess | TRUE | - |
dc.subject.keywordAuthor | Aerospace electronics | - |
dc.subject.keywordAuthor | Computational modeling | - |
dc.subject.keywordAuthor | Computer architecture | - |
dc.subject.keywordAuthor | Convolution | - |
dc.subject.keywordAuthor | convolutional neural network | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | Neural architecture search | - |
dc.subject.keywordAuthor | Search problems | - |
dc.subject.keywordAuthor | Topology | - |
dc.subject.keywordAuthor | Training | - |
dc.citation.endPage | 84798 | - |
dc.citation.startPage | 84790 | - |
dc.citation.title | IEEE Access | - |
dc.citation.volume | 10 | - |
There are no files associated with this item.