Confronta i metodi
Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.
| LSTM a Supervisione Debole× | Long Short-Term Memory (LSTM)× | |
|---|---|---|
| Campo | Apprendimento profondo | Apprendimento profondo |
| Famiglia | Machine learning | Machine learning |
| Anno di origine≠ | 2016–2018 | 1997 |
| Ideatore≠ | Ratner et al. (data programming framework); Hochreiter & Schmidhuber (LSTM backbone) | Hochreiter, S. & Schmidhuber, J. |
| Tipo≠ | Weakly supervised sequence model | Recurrent neural network with gated memory cells |
| Fonte seminale≠ | 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 ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. DOI ↗ |
| Alias | WS-LSTM, noisy-label LSTM, distant-supervision LSTM, data-programming LSTM | LSTM, LSTM network, LSTM-RNN, long short-term memory RNN |
| Correlati≠ | 6 | 4 |
| Sintesi≠ | 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. | Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step. |
| ScholarGateInsieme di dati ↗ |
|
|