Porovnat metody

	Slabě řízené rekurentní neuronové sítě	Slabě supervizovaný Transformer
Obor	Hluboké učení	Hluboké učení
Rodina	Machine learning	Machine learning
Rok vzniku	2009–2016	2017–2019
Tvůrce	Broadly attributed to the weak supervision / distant supervision research community (Mintz et al., 2009; Ratner et al., 2016)	Multiple contributors (weak supervision paradigm: Zhou 2018; transformer backbone: Vaswani et al. 2017)
Typ	Supervised learning under noisy or incomplete labels	Weakly supervised deep learning
Původní zdroj	Ratner, A., De Sa, C., Wu, S., Selsam, D., & Re, C. (2016). Data Programming: Creating Large Training Sets, Quickly. Advances in Neural Information Processing Systems (NeurIPS), 29.	Ratner, A., Bach, S. H., Ehrenberg, H., Fries, J., Wu, S., & Re, C. (2017). Snorkel: Rapid training data creation with weak supervision. Proceedings of the VLDB Endowment, 11(3), 269–282.
Další názvy	WS-RNN, distantly supervised RNN, noise-tolerant RNN, weakly supervised sequence model	WST, weakly supervised attention model, noisy-label transformer, weak supervision with transformers
Příbuzné	5	5
Shrnutí	A weakly supervised RNN trains a recurrent neural network on sequences whose labels come from imperfect sources — heuristic rules, distant supervision, crowdsourcing, or generative label models — rather than expensive expert annotation. This lets researchers exploit large unlabeled corpora for sequential tasks such as text classification, named entity recognition, or time-series prediction when fully annotated data is scarce or costly.	Weakly Supervised Transformer combines the representational power of Transformer architectures with weak supervision strategies that exploit noisy, incomplete, or programmatically generated labels — making it possible to train high-quality NLP and vision models when fully annotated datasets are scarce or prohibitively expensive to produce.