ScholarGate
Msaidizi
Machine learningMachine learning

Jifunze-mwenyewe Kujifundisha kwa Kutumia vipimo

Jifunze-mwenyewe Kujifundisha kwa Kutumia vipimo hufunza kipitishaji (encoder) cha akili bandia ili kuweka vipengele vya pembejeo katika nafasi ya vekta ambapo vitu vinavyofanana maana viko karibu, kwa kutumia lebo za kubuniwa zinazotengenezwa kiotomatiki badala ya maelezo kutoka kwa binadamu. Kwa kuchanganya kazi za awali za kujifunza-mwenyewe na malengo ya vipimo vya kulinganisha au vya tatu (triplet), huzaa uwakilishi unaoweza kuhamishwa na unaohitaji lebo chache, unaofaa kwa utafutaji, kuunganisha (clustering), na uainishaji wa mifano michache (few-shot classification).

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.

Jifunze-mwenyewe Kujifundisha kwa Kutumia vipimo
Mafunzo ya vipimoJifunze kwa KujisimamiaMtandao wa Kifamilia wa…

Vyanzo

  1. Chen, T., Kornblith, S., Norouzi, M., & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. Proceedings of the 37th International Conference on Machine Learning (ICML 2020), PMLR 119, 1597–1607. link
  2. Khosla, P., Tian, Y., Wang, X., Liu, C., Krishnan, D., Isola, P., & Tian, Y. (2020). Supervised Contrastive Learning. Advances in Neural Information Processing Systems (NeurIPS 2020), 33, 18661–18673. link

Jinsi ya kunukuu ukurasa huu

ScholarGate. (2026, June 3). Self-supervised Metric Learning. ScholarGate. https://scholargate.app/sw/machine-learning/self-supervised-metric-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.

Compare side by side
ScholarGateSelf-supervised Metric learning (Self-supervised Metric Learning). Imepatikana 2026-06-15 kutoka https://scholargate.app/sw/machine-learning/self-supervised-metric-learning · Seti ya data: https://doi.org/10.5281/zenodo.20539026