So sánh phương pháp

	LSTM Giám sát Yếu	Mạng nơ-ron hồi quy
Lĩnh vực	Học sâu	Học sâu
Họ	Machine learning	Machine learning
Năm ra đời	2016–2018	1986–1990
Người khởi xướng	Ratner et al. (data programming framework); Hochreiter & Schmidhuber (LSTM backbone)	Rumelhart, D. E.; Elman, J. L.
Loại	Weakly supervised sequence model	Sequential neural network
Công trình gốc	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.	Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211.
Tên gọi khác	WS-LSTM, noisy-label LSTM, distant-supervision LSTM, data-programming LSTM	RNN, Elman network, Jordan network, simple recurrent network
Liên quan	6	3
Tóm tắt	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.	A Recurrent Neural Network (RNN) is a class of neural network designed to process sequential data by maintaining a hidden state that carries information across time steps. Introduced in its modern form by Rumelhart et al. (1986) and further shaped by Elman (1990), RNNs became the dominant architecture for sequence modelling in NLP, speech, and time-series analysis before the rise of attention-based models.