Translations:Softmax Function/8/zh: Difference between revisions

Latest revision as of 23:41, 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)

The softmax function amplifies differences between {{Term|logits}}. A {{Term|logits|logit}} that is larger than its peers receives a disproportionately large share of the probability mass because the exponential function grows super-linearly. For example:

softmax 函数会放大 logits 之间的差异。大于其他值的 logit 由于指数函数呈超线性增长而获得不成比例的概率质量份额。例如：

Revision as of 22:03, 27 April 2026 (view source) DeployBot (talk \| contribs) (Batch translate Softmax Function unit 8 → zh) Tag: translation ← Older edit		Latest revision as of 23:41, 27 April 2026 (view source) DeployBot (talk \| contribs) (Batch translate Softmax Function unit 8 → zh) Tag: translation
Line 1:		Line 1:
	softmax 函数会放大 logits ~~之间的差异。比其他值更大的~~ logit ~~会获得不成比例的概率质量，因为指数函数以超线性方式增长。例如：~~		softmax 函数会放大 {{Term\|logits}} 之间的差异。大于其他值的 {{Term\|logits\|logit}} 由于指数函数呈超线性增长而获得不成比例的概率质量份额。例如：