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 !! Description !! Typical application |- | '''Standard dropout''' || Drops individual neurons || Fully connected layers |- | '''{{Term|spatial dropout}}''' || Drops entire feature {{Term|map|maps}} ({{Term|feature map|channels}}) || {{Term|convolutional neural network|Convolutional networks}} |- | '''DropConnect''' || Drops individual weights instead of neurons || Dense layers |- | '''Variational dropout''' || Learns the dropout rate per neuron/weight || {{Term|bayesian deep learning}} |- | '''DropBlock''' || Drops contiguous regions of feature {{Term|map|maps}} || {{Term|convolutional neural network|Convolutional networks}} |- | '''Alpha dropout''' || Maintains self-normalizing property (for {{Term|selu}} {{Term|activation function|activations}}) || Self-normalizing networks |} |
| h Spanish (es) | {| class="wikitable" |- ! Variante !! Descripción !! Aplicación típica |- | '''Dropout estándar''' || Descarta neuronas individuales || Capas totalmente conectadas |- | '''{{Term|spatial dropout|dropout espacial}}''' || Descarta {{Term|map|mapas}} de características enteros ({{Term|feature map|canales}}) || {{Term|convolutional neural network|Redes convolucionales}} |- | '''DropConnect''' || Descarta pesos individuales en lugar de neuronas || Capas densas |- | '''Dropout variacional''' || Aprende la tasa de dropout por neurona/peso || {{Term|bayesian deep learning|Aprendizaje profundo bayesiano}} |- | '''DropBlock''' || Descarta regiones contiguas de {{Term|map|mapas}} de características || {{Term|convolutional neural network|Redes convolucionales}} |- | '''Alpha dropout''' || Mantiene la propiedad auto-normalizante (para {{Term|activation function|activaciones}} {{Term|selu|SELU}}) || Redes auto-normalizantes |} |
| h Chinese (zh) | {| class="wikitable" |- ! 变体 !! 描述 !! 典型应用 |- | '''标准 dropout''' || 丢弃单个神经元 || 全连接层 |- | '''{{Term|spatial dropout|空间 dropout}}''' || 丢弃整个特征{{Term|map|图}}({{Term|feature map|通道}}) || {{Term|convolutional neural network|卷积网络}} |- | '''DropConnect''' || 丢弃单个权重而不是神经元 || 密集层 |- | '''变分 dropout''' || 学习每个神经元/权重的 dropout 率 || {{Term|bayesian deep learning|贝叶斯深度学习}} |- | '''DropBlock''' || 丢弃特征{{Term|map|图}}的连续区域 || {{Term|convolutional neural network|卷积网络}} |- | '''Alpha dropout''' || 保持自归一化特性(用于 {{Term|selu|SELU}} {{Term|activation function|激活}}) || 自归一化网络 |} |