Porovnat metody
Prohlédněte si vybrané metody vedle sebe; řádky, které se liší, jsou zvýrazněny.
| FastText× | Rekurentní neuronová síť× | |
|---|---|---|
| Obor | Hluboké učení | Hluboké učení |
| Rodina | Machine learning | Machine learning |
| Rok vzniku≠ | 2016 | 1986–1990 |
| Tvůrce≠ | Joulin, A.; Bojanowski, P.; Grave, E.; Mikolov, T. (Facebook AI Research) | Rumelhart, D. E.; Elman, J. L. |
| Typ≠ | Subword embedding model and linear text classifier | Sequential neural network |
| Původní zdroj≠ | Joulin, A., Grave, E., Bojanowski, P. & Mikolov, T. (2017). Bag of Tricks for Efficient Text Classification. In Proceedings of EACL 2017, Short Papers, pp. 427–431. ACL. DOI ↗ | Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. DOI ↗ |
| Další názvy≠ | fastText, fast text, subword embedding, character n-gram embedding | RNN, Elman network, Jordan network, simple recurrent network |
| Příbuzné≠ | 2 | 3 |
| Shrnutí≠ | FastText is a word embedding and text classification framework developed by Facebook AI Research (Joulin, Bojanowski, Grave, and Mikolov, 2016–2017) that represents each word as the sum of its character n-gram vectors, allowing it to construct meaningful representations for unseen and morphologically rich words and to perform near state-of-the-art text classification orders of magnitude faster than deep neural network alternatives. | 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. |
| ScholarGateDatová sada ↗ |
|
|