Translations:Softmax Function/10/en: Difference between revisions

Latest revision as of 23:34, 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 (Softmax Function)

As the gap between the largest {{Term|logits|logit}} and the others increases, the output approaches a {{Term|one-hot encoding|one-hot}} vector. This "winner-take-most" behavior makes softmax well-suited for classification where a single class should dominate.

As the gap between the largest logit and the others increases, the output approaches a one-hot vector. This "winner-take-most" behavior makes softmax well-suited for classification where a single class should dominate.

Revision as of 22:02, 27 April 2026 (view source) FuzzyBot (talk \| contribs) (Importing a new version from external source) Tag: Manual revert ← Older edit		Latest revision as of 23:34, 27 April 2026 (view source) FuzzyBot (talk \| contribs) (Importing a new version from external source) Tag: Manual revert
Line 1:		Line 1:
	As the gap between the largest logit and the others increases, the output approaches a one-hot vector. This "winner-take-most" behavior makes softmax well-suited for classification where a single class should dominate.		As the gap between the largest {{Term\|logits\|logit}} and the others increases, the output approaches a {{Term\|one-hot encoding\|one-hot}} vector. This "winner-take-most" behavior makes softmax well-suited for classification where a single class should dominate.