Usporedite metode
Pregledajte odabrane metode jednu uz drugu; retci koji se razlikuju su istaknuti.
| Ugođeni rekurentni neuronski sklop× | Dugo kratkoročno pamćenje (LSTM)× | |
|---|---|---|
| Područje | Duboko učenje | Duboko učenje |
| Obitelj | Machine learning | Machine learning |
| Godina nastanka≠ | 2015–2018 | 1997 |
| Tvorac≠ | Popularised by Howard & Ruder (ULMFiT, 2018); RNN fine-tuning concept developed iteratively in the NLP community from ~2015 | Hochreiter, S. & Schmidhuber, J. |
| Vrsta≠ | Transfer learning / sequential model adaptation | Recurrent neural network with gated memory cells |
| Temeljni izvor≠ | Howard, J. & Ruder, S. (2018). Universal Language Model Fine-Tuning for Text Classification. Proceedings of ACL 2018, 328–339. DOI ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. DOI ↗ |
| Drugi nazivi | Fine-Tuned RNN, RNN Fine-Tuning, domain-adapted RNN, pre-trained RNN with downstream adaptation | LSTM, LSTM network, LSTM-RNN, long short-term memory RNN |
| Srodne≠ | 6 | 4 |
| Sažetak≠ | A Fine-Tuned Recurrent Neural Network (RNN) starts from a model pre-trained on large corpora or time-series data and adapts its weights to a specific downstream task through controlled gradient updates. The approach dramatically cuts the labeled data needed for strong sequence modeling performance in text classification, named entity recognition, sentiment analysis, and related tasks. | 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. |
| ScholarGateSkup podataka ↗ |
|
|