השוואת שיטות

	GRU בפיקוח חלש	LSTM מפוקח-בקושי
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2014–2016	2016–2018
הוגה השיטה	Chung et al. (GRU); Ratner et al. (weak supervision framework)	Ratner et al. (data programming framework); Hochreiter & Schmidhuber (LSTM backbone)
סוג	Weakly supervised sequence model	Weakly supervised sequence model
מקור מכונן	Ratner, A. J., De Sa, C. M., Wu, S., Selsam, D., & Re, C. (2016). Data Programming: Creating Large Training Sets, Quickly. Advances in Neural Information Processing Systems (NeurIPS), 29.	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.
כינויים	WS-GRU, GRU with weak supervision, weakly labeled GRU, noisy-label GRU	WS-LSTM, noisy-label LSTM, distant-supervision LSTM, data-programming LSTM
קשורות	6	6
תקציר	Weakly Supervised GRU trains a Gated Recurrent Unit network on sequences labeled by imperfect, heuristic, or programmatic sources rather than costly hand-annotated ground truth. It combines the GRU's efficiency at capturing temporal dependencies with weak-supervision techniques that aggregate noisy labels, enabling practical sequence modeling when large fully labeled datasets are unavailable.	Weakly supervised LSTM trains a Long Short-Term Memory network on sequence data where clean, manually annotated labels are scarce or absent. Instead, multiple imperfect label sources — heuristic rules, distant supervision, crowdsourcing, or programmatic labeling functions — are combined to produce probabilistic training labels, which are then used to supervise the LSTM. This allows scalable training on large unlabeled corpora without exhaustive human annotation.