Compară metode
Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.
| Long Short-Term Memory (LSTM)× | Rețea Neuronală Recurentă× | |
|---|---|---|
| Domeniu | Învățare profundă | Învățare profundă |
| Familie | Machine learning | Machine learning |
| Anul apariției≠ | 1997 | 1986–1990 |
| Autorul original≠ | Hochreiter, S. & Schmidhuber, J. | Rumelhart, D. E.; Elman, J. L. |
| Tip≠ | Recurrent neural network with gated memory cells | Sequential neural network |
| Sursa seminală≠ | Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. DOI ↗ | Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. DOI ↗ |
| Denumiri alternative | LSTM, LSTM network, LSTM-RNN, long short-term memory RNN | RNN, Elman network, Jordan network, simple recurrent network |
| Înrudite≠ | 4 | 3 |
| Rezumat≠ | 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. | 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. |
| ScholarGateSet de date ↗ |
|
|