ScholarGate
Msaidizi
Machine learning

ResNet (Mtandao wa Mabaki)

ResNet (Mtandao wa Mabaki) ni usanifu wa kina wa mtandao wa neva wa konvolusheni ulioanzishwa na Kaiming He, Xiangyu Zhang, Shaoqing Ren, na Jian Sun katika CVPR 2016. Kwa kuingiza miunganisho ya njia ya mkato (ruka) ambayo hubeba pembejeo ya kizuizi moja kwa moja kwenye towe lake — ikifafanua kazi ya kizuizi kama kujifunza marekebisho ya mabaki badala ya ramani kamili — ResNet iliwezesha mafunzo ya mitandao yenye mamia au hata maelfu ya tabaka bila uharibifu wa kupungua kwa gradian ambazo hapo awali zilifanya mitandao mirefu sana kuwa haitekelezeki. Ilishinda shindano la utambuzi wa picha la ILSVRC 2015 na kosa la juu la 5% la 3.57% na bado inabaki kuwa usanifu wa uti wa mgongo unaotumiwa sana katika maono ya kompyuta.

Fungua katika MethodMindHivi karibuniVideoHivi karibuniDownload slides

Soma mbinu kamili

Kwa wanachama pekee

Ingia kwa akaunti ya bure ili kusoma sehemu hii.

Ingia

Method map

The neighbourhood of related methods — select a node to explore.

+1 more

Vyanzo

  1. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep Residual Learning for Image Recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. DOI: 10.1109/CVPR.2016.90
  2. He, K., Zhang, X., Ren, S., & Sun, J. (2015). Deep Residual Learning for Image Recognition. arXiv:1512.03385. link
  3. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning (Ch. 9: Convolutional Networks). MIT Press. ISBN: 978-0-262-03561-3

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Residual Network (ResNet). ScholarGate. https://scholargate.app/sw/deep-learning/resnet

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Imerejelewa na

ScholarGateResNet (Residual Network (ResNet)). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/deep-learning/resnet · Seti ya data: https://doi.org/10.5281/zenodo.20539026