ScholarGate
Asistent
Machine learning

Višeglava samopažnja

Višeglava samopažnja (engl. Multi-head self-attention), koju su 2017. uveli Vaswani i suradnici, mehanizam je koji omogućuje svakoj poziciji u nizu da paralelno izračuna svoj odnos sa svim ostalim pozicijama. To je srž arhitekture Transformer i temelj BERT-a, GPT-a i T5.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

Višeglava samopažnja
Prilagođavanje BERT-a (B…Prilagođavanje GPT model…LoRA i PEFTSlučajna šumaXGBoostAttention MechanismBidirectional RNNRetrieval-Augmented Gene…Model "sekvenca-u-sekven…

Izvori

  1. Vaswani, A. et al. (2017). Attention Is All You Need. NeurIPS. link ↗
  2. Devlin, J. et al. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL. link ↗

Kako citirati ovu stranicu

ScholarGate. (2026, June 1). Multi-Head Self-Attention (Transformer Core). ScholarGate. https://scholargate.app/hr/deep-learning/self-attention-transformer

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side →

Citirana u

Attention MechanismBidirectional RNNRetrieval-Augmented Generation (RAG)Model "sekvenca-u-sekvencu"

Uočili ste pogrešku na ovoj stranici? Prijavite je ili predložite ispravak →

ScholarGate — Self-Attention (Multi-Head Self-Attention (Transformer Core)). Preuzeto 2026-06-15 s https://scholargate.app/hr/deep-learning/self-attention-transformer · Skup podataka: https://doi.org/10.5281/zenodo.20539026