Compară metode
Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.
| RNN bidirecțional× | Atenție Multi-Capete (Multi-Head Self-Attention)× | Model Secvență-la-Secvență× | |
|---|---|---|---|
| Domeniu | Învățare profundă | Învățare profundă | Învățare profundă |
| Familie | Machine learning | Machine learning | Machine learning |
| Anul apariției≠ | 1997 | 2017 | 2014 |
| Autorul original≠ | Schuster, M. & Paliwal, K.K. | Vaswani, A. et al. | Sutskever, I.; Cho, K. |
| Tip≠ | Recurrent neural network (sequence model) | Attention mechanism (Transformer core) | Encoder-decoder neural network (deep learning) |
| Sursa seminală≠ | 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 ↗ | Sutskever, I., Vinyals, O. & Le, Q. V. (2014). Sequence to Sequence Learning with Neural Networks. NeurIPS. link ↗ |
| Denumiri alternative≠ | 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 | Dizi-Dizi Modeli (Seq2Seq — Encoder-Decoder), encoder-decoder model, seq2seq, sequence to sequence learning |
| Înrudite | 5 | 5 | 5 |
| Rezumat≠ | 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. | The sequence-to-sequence (Seq2Seq) model, introduced by Sutskever, Vinyals and Le and by Cho and colleagues in 2014, is an encoder-decoder neural network that maps a variable-length input sequence to a variable-length output sequence. It is the foundation of machine translation, text summarization, dialogue systems and code generation. |
| ScholarGateSet de date ↗ |
|
|
|