All translations
Enter a message name below to show all available translations.
Found 3 translations.
| Name | Current message text |
|---|---|
| h English (en) | The size of each {{Term|training step|step}} is controlled by a {{Term|scalar}} called the '''{{Term|learning rate}}''' (often denoted <math>\eta</math>). A large {{Term|learning rate}} covers ground quickly but risks overshooting the minimum; a small {{Term|learning rate}} converges more reliably but may take prohibitively many {{Term|training step|steps}}. |
| h Spanish (es) | El tamaño de cada {{Term|training step|paso}} está controlado por un {{Term|scalar|escalar}} llamado '''{{Term|learning rate|tasa de aprendizaje}}''' (a menudo denotado <math>\eta</math>). Una {{Term|learning rate|tasa de aprendizaje}} grande cubre terreno rápidamente pero corre el riesgo de sobrepasar el mínimo; una {{Term|learning rate|tasa de aprendizaje}} pequeña converge de forma más confiable pero puede requerir un número prohibitivo de {{Term|training step|pasos}}. |
| h Chinese (zh) | 每一{{Term|training step|步}}的大小由一个称为'''{{Term|learning rate|学习率}}'''的{{Term|scalar|标量}}（通常记作 <math>\eta</math>）控制。较大的{{Term|learning rate|学习率}}能快速覆盖范围，但有越过最小值的风险；较小的{{Term|learning rate|学习率}}收敛更可靠，但可能需要数量惊人的{{Term|training step|步骤}}。 |