Attention Mechanism

attentiontransformerneural-networksdeep-learningsequence-modelingself-attentionmachine-learning

Definition

An attention mechanism lets a neural network compute each output element as a data-dependent weighted average of a set of value vectors, where the weights measure the relevance ("compatibility") of a query to each key. The Transformer (Vaswani et al. 2017) builds an entire sequence model out of attention alone — dispensing with recurrence and convolution — and is the architecture underlying modern large language models (Vaswani et al. 2017).

Key Ideas

Why It Matters

Open Questions

Related