Krahasoni metodat
Shqyrtoni metodat e zgjedhura krah për krah; rreshtat që ndryshojnë janë të theksuar.
| LSTM me Mbikëqyrje të Dobët× | Rrjeti Nervor Rekurent× | |
|---|---|---|
| Fusha | Mësimi i thellë | Mësimi i thellë |
| Familja | Machine learning | Machine learning |
| Viti i origjinës≠ | 2016–2018 | 1986–1990 |
| Krijuesi≠ | Ratner et al. (data programming framework); Hochreiter & Schmidhuber (LSTM backbone) | Rumelhart, D. E.; Elman, J. L. |
| Lloji≠ | Weakly supervised sequence model | Sequential neural network |
| Burimi themelues≠ | 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. link ↗ | Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. DOI ↗ |
| Emërtime të tjera | WS-LSTM, noisy-label LSTM, distant-supervision LSTM, data-programming LSTM | RNN, Elman network, Jordan network, simple recurrent network |
| Të lidhura≠ | 6 | 3 |
| Përmbledhja≠ | 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. |
| ScholarGateSeti i të dhënave ↗ |
|
|