All translations
Enter a message name below to show all available translations.
Found 3 translations.
| Name | Current message text |
|---|---|
| h English (en) | {| class="wikitable" |- ! Variant !! Gradient computed over !! Per-{{Term|training step|step}} cost !! {{Term|gradient noise injection|Gradient noise}} |- | '''Batch (full) gradient descent''' || All <math>N</math> samples || High || None |- | '''{{Term|stochastic gradient descent}} ({{Term|stochastic gradient descent|SGD}})''' || 1 random sample || Low || High |- | '''{{Term|mini-batch}} gradient descent''' || <math>B</math> random samples (<math>1 < B < N</math>) || Medium || Medium |} |
| h Spanish (es) | {| class="wikitable" |- ! Variante !! Gradiente calculado sobre !! Coste por {{Term|training step|paso}} !! {{Term|gradient noise injection|Ruido del gradiente}} |- | '''Descenso de gradiente por lotes (completo)''' || Todas las <math>N</math> muestras || Alto || Ninguno |- | '''{{Term|stochastic gradient descent|Descenso de gradiente estocástico}} ({{Term|stochastic gradient descent|SGD}})''' || 1 muestra aleatoria || Bajo || Alto |- | '''Descenso de gradiente por {{Term|mini-batch|minilotes}}''' || <math>B</math> muestras aleatorias (<math>1 < B < N</math>) || Medio || Medio |} |
| h Chinese (zh) | {| class="wikitable" |- ! 变体 !! 梯度的计算依据 !! 每{{Term|training step|步}}成本 !! {{Term|gradient noise injection|梯度噪声}} |- | '''批量（全量）梯度下降''' || 全部 <math>N</math> 个样本 || 高 || 无 |- | '''{{Term|stochastic gradient descent|随机梯度下降}}（{{Term|stochastic gradient descent|SGD}}）''' || 1 个随机样本 || 低 || 高 |- | '''{{Term|mini-batch|小批量}}梯度下降''' || <math>B</math> 个随机样本（<math>1 < B < N</math>） || 中 || 中 |} |