Machine learningDeep learning / NLP / CV

Objašnjivi Transformer

Objašnjivi Transformer kombinira standardnu ili pred-obučenu Transformer arhitekturu s post-hoc ili ugrađenim tehnikama interpretabilnosti — kao što su attention rollout, gradient-weighted attention ili SHAP — kako bi se otkrilo koji su ulazni tokeni ili regije potaknuli svako predviđanje. Pristup spaja visoku prediktivnu točnost s transparentnošću potrebnom u domenama visokog rizika ili reguliranim domenama.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

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

+4 more

Izvori

  1. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. link
  2. Chefer, H., Gur, S., & Wolf, L. (2021). Transformer interpretability beyond attention visualization. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 782–791. DOI: 10.1109/CVPR46437.2021.00084

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Explainable Transformer (Interpretability-Augmented Transformer Model). ScholarGate. https://scholargate.app/hr/deep-learning/explainable-transformer

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

Citirana u

ScholarGateExplainable Transformer (Explainable Transformer (Interpretability-Augmented Transformer Model)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/explainable-transformer · Skup podataka: https://doi.org/10.5281/zenodo.20539026