Mafunzo ya uhamishaji yanayojisimamia
Mafunzo ya uhamishaji yanayojisimamia huunganisha mbinu mbili zenye nguvu: kwanza, mfumo hujifunza uwakilishi tajiri kutoka kwa data isiyo na lebo kwa kutumia kazi za awali za kujisimamia, kisha uwakilishi huo uliojifunzwa huhamishwa na kurekebishwa kwa kazi inayofuata yenye data chache yenye lebo. Mbinu hii ndiyo msingi wa mifumo muhimu kama vile BERT katika NLP na SimCLR na DINO katika taswira, ikipunguza sana mahitaji ya data yenye lebo katika nyanja nyingi.
Soma mbinu kamili
Ingia kwa akaunti ya bure ili kusoma sehemu hii.
Method map
The neighbourhood of related methods — select a node to explore.
Vyanzo
- Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A simple framework for contrastive learning of visual representations. In Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 1597–1607. link ↗
- Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT 2019, 4171–4186. Association for Computational Linguistics. DOI: 10.18653/v1/N19-1423 ↗
Jinsi ya kunukuu ukurasa huu
ScholarGate. (2026, June 3). Self-supervised Pre-training for Transfer Learning. ScholarGate. https://scholargate.app/sw/machine-learning/self-supervised-transfer-learning
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.
- Kujifunza kwa Kiasi Kidogo cha MifanoUjifunzaji wa Mashine↔ compare
- Mafunzo ya vipimoUjifunzaji wa Mashine↔ compare
- Kujifunza kwa Kujitegemea kwa Kiasi Kidogo (SSL-FSL)Ujifunzaji wa Mashine↔ compare
- Jifunze kwa KujisimamiaUjifunzaji wa Mashine↔ compare
- Ujifunzaji Nusu-SimamiwaUjifunzaji wa Mashine↔ compare
- Kujifunza kwa uhamishajiUjifunzaji wa Mashine↔ compare
Umeona tatizo kwenye ukurasa huu? Ripoti au pendekeza marekebisho →