Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| Sieć stanów echa (Echo State Network, ESN)× | LSTM× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania≠ | 2004 | 1997 |
| Twórca≠ | Herbert Jaeger & Harald Haas | Hochreiter, S. & Schmidhuber, J. |
| Typ≠ | Recurrent neural network with fixed random reservoir | Recurrent neural network (gated memory cell) |
| Źródło pierwotne≠ | Jaeger, H., & Haas, H. (2004). Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science, 304(5667), 78–80. DOI ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long Short-Term Memory. Neural Computation, 9(8), 1735–1780. DOI ↗ |
| Inne nazwy | ESN, Liquid State Machine (related formulation), Reservoir Computing, Yankı Durum Ağı | LSTM (Uzun Kısa Dönem Bellek Ağı), long short-term memory, LSTM network, recurrent neural network with memory cells |
| Pokrewne≠ | 3 | 5 |
| Podsumowanie≠ | An Echo State Network (ESN) is a type of recurrent neural network introduced by Herbert Jaeger and Harald Haas in 2004 that exploits a large, randomly connected, fixed recurrent layer — the reservoir — to project input signals into a high-dimensional nonlinear space. Only the linear output weights are trained, typically via ridge regression, making ESNs computationally inexpensive yet highly expressive for temporal and chaotic time-series modeling tasks. | LSTM (Long Short-Term Memory) is a recurrent neural network architecture, introduced by Sepp Hochreiter and Jürgen Schmidhuber in 1997, that can learn long-term dependencies in sequential data and is widely used for time-series and sequence prediction. It keeps an internal memory that lets information persist across many time steps. |
| ScholarGateZbiór danych ↗ |
|
|