So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| Tìm kiếm Kiến trúc Mạng Nơ-ron× | Longformer / BigBird× | |
|---|---|---|
| Lĩnh vực | Học sâu | Học sâu |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 2017 | 2020 |
| Người khởi xướng≠ | Zoph, B. & Le, Q.V. | Beltagy, Peters & Cohan (Longformer); Zaheer et al. (BigBird) |
| Loại≠ | Automated architecture optimization (deep learning) | Sparse-attention Transformer for long sequences |
| Công trình gốc≠ | Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR. link ↗ | Beltagy, I., Peters, M. E. & Cohan, A. (2020). Longformer: The Long-Document Transformer. arXiv. link ↗ |
| Tên gọi khác | Nöral Mimari Arama (NAS), NAS, automated architecture design, differentiable architecture search | Uzun Dizi Transformer (Longformer / BigBird), uzun dizi transformer, long-document transformer, sparse-attention transformer |
| Liên quan≠ | 5 | 4 |
| Tóm tắt≠ | Neural Architecture Search (NAS), introduced by Zoph and Le in 2017, automatically optimizes architectural decisions such as a network's depth, width, and connection structure instead of hand-designing them. Leading methods in the field include DARTS, ENAS, and Once-for-All. | Long-sequence Transformers such as Longformer (Beltagy, Peters & Cohan, 2020) and BigBird (Zaheer et al., 2020) replace the standard Transformer's O(n²) attention with sparse attention patterns that scale linearly, O(n), with sequence length. This lets a single model attend over thousands of tokens — full documents, legal texts, or genomic sequences — that would not fit a conventional Transformer. |
| ScholarGateBộ dữ liệu ↗ |
|
|