Translations:Softmax Function/19/zh: Difference between revisions

Revision as of 22:04, 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)

This is mathematically equivalent (the constant cancels) but ensures the largest exponent is <math>e^0 = 1</math>, preventing overflow. All major {{Term|deep learning}} frameworks implement this stabilized version automatically.

这在数学上是等价的（常数会抵消），但能确保最大指数为 $$ e^0 = 1 $$ ，从而防止溢出。所有主流深度学习框架都会自动实现这一稳定化版本。

Revision as of 03:17, 27 April 2026 (view source) DeployBot (talk \| contribs) (Batch translate Softmax Function unit 19 → zh) Tag: translation		Revision as of 22:04, 27 April 2026 (view source) DeployBot (talk \| contribs) (Batch translate Softmax Function unit 19 → zh) Tag: translation Newer edit →
Line 1:		Line 1:
	~~这在数学上是等价的（常数会抵消），但确保最大的指数为~~ <math>e^0 = 1</math>~~，从而防止溢出。所有主要的深度学习框架都会自动实现这个稳定化版本。~~		这在数学上是等价的（常数会抵消），但能确保最大指数为 <math>e^0 = 1</math>，从而防止溢出。所有主流深度学习框架都会自动实现这一稳定化版本。