Σύγκριση μεθόδων
Εξετάστε τις επιλεγμένες μεθόδους δίπλα-δίπλα· οι γραμμές που διαφέρουν επισημαίνονται.
| Αμφίδρομο RNN× | Αυτο-προσοχή πολλαπλών κεφαλών× | |
|---|---|---|
| Πεδίο | Βαθιά Μάθηση | Βαθιά Μάθηση |
| Οικογένεια | Machine learning | Machine learning |
| Έτος προέλευσης≠ | 1997 | 2017 |
| Δημιουργός≠ | Schuster, M. & Paliwal, K.K. | Vaswani, A. et al. |
| Τύπος≠ | Recurrent neural network (sequence model) | Attention mechanism (Transformer core) |
| Θεμελιώδης πηγή≠ | Schuster, M. & Paliwal, K.K. (1997). Bidirectional Recurrent Neural Networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681. DOI ↗ | Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS. link ↗ |
| Εναλλακτικές ονομασίες≠ | Çift Yönlü RNN / BiLSTM / BiGRU, bidirectional recurrent neural network, BiLSTM, BiGRU | Öz-Dikkat ve Çok Başlı Dikkat (Multi-Head Self-Attention), öz-dikkat, multi-head attention, scaled dot-product attention |
| Συναφείς | 5 | 5 |
| Σύνοψη≠ | A Bidirectional RNN, introduced by Schuster and Paliwal in 1997, processes a sequence in both forward and backward directions so that every position has access to its full surrounding context. With LSTM or GRU cells (BiLSTM/BiGRU) it is the standard approach for named-entity recognition, sequence labelling, and speech recognition. | Multi-head self-attention, introduced by Vaswani and colleagues in 2017, is the mechanism that lets every position in a sequence compute its relationship to all other positions in parallel. It is the core of the Transformer architecture and the foundation underneath BERT, GPT, and T5. |
| ScholarGateΣύνολο δεδομένων ↗ |
|
|