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

Revision as of 22:03, 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。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：

Revision as of 03:17, 27 April 2026 (view source) DeployBot (talk \| contribs) (Batch translate Softmax Function unit 8 → zh) Tag: translation		Revision as of 22:03, 27 April 2026 (view source) DeployBot (talk \| contribs) (Batch translate Softmax Function unit 8 → zh) Tag: translation Newer edit →
Line 1:		Line 1:
	softmax 函数会放大 logits ~~之间的差异。比其同类更大的~~ logit ~~会获得不成比例的大量概率质量，因为指数函数以超线性方式增长。例如：~~		softmax 函数会放大 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：