liveBook · Manning

Query

As explained in Applied Reinforcement Learning

A query is an attention vector representing the information an input element seeks from other elements.

A query is a vector derived from a zone’s representation that expresses what information it seeks from other zones. Comparing it with other zones’ keys produces relevance scores; those scores weight the values used to form the zone’s output. section 9.5

Figure 9.6 The Attention Mechanism — Query, Key, Value.

See how queries, keys, and values combine in the attention mechanism. section 9.5

How Applied Reinforcement Learning covers it

How deep it goes
Defines queries as transformed zone representations and explains their dot-product comparison with keys, without detailing vector construction.
Examples
Uses zones seeking relevant information from other zones to illustrate query-key comparisons.
What you can do after
Understand how query-key similarity determines which zones contribute information to a zone’s output.
How it connects
Connects queries to keys, values, attention weights, and softmax.

Also explained in

Compare how 14 books explain query →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Applied Reinforcement Learning. The section links point to the parts of the book it draws on.