Compară metode

	Căutarea Arhitecturilor Neuronale	Longformer / BigBird
Domeniu	Învățare profundă	Învățare profundă
Familie	Machine learning	Machine learning
Anul apariției	2017	2020
Autorul original	Zoph, B. & Le, Q.V.	Beltagy, Peters & Cohan (Longformer); Zaheer et al. (BigBird)
Tip	Automated architecture optimization (deep learning)	Sparse-attention Transformer for long sequences
Sursa seminală	Zoph, B. & Le, Q.V. (2017). Neural Architecture Search with Reinforcement Learning. ICLR.	Beltagy, I., Peters, M. E. & Cohan, A. (2020). Longformer: The Long-Document Transformer. arXiv.
Denumiri alternative	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
Înrudite	5	4
Rezumat	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.