Transformer Zinazoeleka
Transformer Zinazoeleka huunganisha usanifu wa kawaida au uliopewa mafunzo awali wa Transformer na mbinu za utendakazi wa baada ya uchanganuzi au zilizo ndani — kama vile utoaji wa umakini (attention rollout), umakini wenye uzito wa mteremko (gradient-weighted attention), au SHAP — ili kufichua ni tokeni au sehemu zipi za pembejeo zilizoathiri kila utabiri. Mbinu hii huunganisha usahihi wa juu wa utabiri na uwazi unaohitajika katika nyanja zenye dhamana kubwa au zilizo na udhibiti.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
+4 more
Vyanzo
- 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 ↗
- 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 ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Explainable Transformer (Interpretability-Augmented Transformer Model). ScholarGate. https://scholargate.app/sw/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.
- Uainishaji unaotumia BERTUjifunzaji wa Kina↔ compare
- Ufafanuzi wa Uainishaji wa BERTUjifunzaji wa Kina↔ compare
- Transformeri wa MultimodalUjifunzaji wa Kina↔ compare
- Transformer Inayojisimamia KujifunzaUjifunzaji wa Kina↔ compare
Imerejelewa na
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →