Translations:Attention Mechanisms/27/es: Difference between revisions

Revision as of 21:58, 27 April 2026

Information about message (contribute)

This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.

Message definition (Attention Mechanisms)

Because self-attention is permutation-invariant (it treats the input as an unordered set), positional information must be injected explicitly. The original {{Term|transformer}} uses sinusoidal encodings:

Dado que la autoatención es invariante a permutaciones (trata la entrada como un conjunto no ordenado), la información posicional debe inyectarse de manera explícita. El Transformer original utiliza codificaciones sinusoidales:

Revision as of 03:21, 27 April 2026 (view source) DeployBot (talk \| contribs) (Batch translate Attention Mechanisms unit 27 → es) Tag: translation		Revision as of 21:58, 27 April 2026 (view source) DeployBot (talk \| contribs) (Batch translate Attention Mechanisms unit 27 → es) Tag: translation Newer edit →
Line 1:		Line 1:
	Dado que la autoatención es invariante a permutaciones (trata la entrada como un conjunto ~~sin orden~~), la información posicional debe inyectarse ~~explícitamente~~. El Transformer original utiliza codificaciones sinusoidales:		Dado que la autoatención es invariante a permutaciones (trata la entrada como un conjunto no ordenado), la información posicional debe inyectarse de manera explícita. El Transformer original utiliza codificaciones sinusoidales: