Translations:Softmax Function/17/en: Difference between revisions
(Importing a new version from external source) |
(Importing a new version from external source) Tag: Manual revert |
||
| (2 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
A naive implementation of softmax can overflow when logits are large (e.g., <math>e^{1000}</math> is infinite in floating point). The standard fix subtracts the maximum logit: | A naive implementation of softmax can overflow when {{Term|logits}} are large (e.g., <math>e^{1000}</math> is infinite in floating point). The standard fix subtracts the maximum {{Term|logits|logit}}: | ||
Latest revision as of 23:34, 27 April 2026
A naive implementation of softmax can overflow when logits are large (e.g., $ e^{1000} $ is infinite in floating point). The standard fix subtracts the maximum logit: