All translations
Enter a message name below to show all available translations.
Found 3 translations.
| Name | Current message text |
|---|---|
| h English (en) | {| class="wikitable" |- ! Function !! Formula !! Range !! Notes |- | '''Sigmoid''' || <math>\sigma(z) = \frac{1}{1+e^{-z}}</math> || (0, 1) || Historically popular; suffers from vanishing gradients |- | '''Tanh''' || <math>\tanh(z) = \frac{e^z - e^{-z}}{e^z + e^{-z}}</math> || (−1, 1) || Zero-centred; still saturates for large inputs |- | '''ReLU''' || <math>\max(0, z)</math> || [0, ∞) || Default choice in modern networks; can cause "dead neurons" |- | '''Leaky ReLU''' || <math>\max(\alpha z, z)</math> for small <math>\alpha > 0</math> || (−∞, ∞) || Addresses the dead-neuron problem |- | '''Softmax''' || <math>\frac{e^{z_i}}{\sum_j e^{z_j}}</math> || (0, 1) || Used in output layer for multi-class classification |} |
| h Spanish (es) | {| class="wikitable" |- ! Función !! Fórmula !! Rango !! Observaciones |- | '''Sigmoide''' || <math>\sigma(z) = \frac{1}{1+e^{-z}}</math> || (0, 1) || Históricamente popular; sufre de gradientes que se desvanecen |- | '''Tanh''' || <math>\tanh(z) = \frac{e^z - e^{-z}}{e^z + e^{-z}}</math> || (−1, 1) || Centrada en cero; aún se satura para entradas grandes |- | '''ReLU''' || <math>\max(0, z)</math> || [0, ∞) || Opción por defecto en redes modernas; puede causar "neuronas muertas" |- | '''Leaky ReLU''' || <math>\max(\alpha z, z)</math> para <math>\alpha > 0</math> pequeño || (−∞, ∞) || Aborda el problema de las neuronas muertas |- | '''Softmax''' || <math>\frac{e^{z_i}}{\sum_j e^{z_j}}</math> || (0, 1) || Se utiliza en la capa de salida para clasificación multiclase |} |
| h Chinese (zh) | {| class="wikitable" |- ! 函数 !! 公式 !! 范围 !! 备注 |- | '''Sigmoid''' || <math>\sigma(z) = \frac{1}{1+e^{-z}}</math> || (0, 1) || 历史上很流行；存在梯度消失问题 |- | '''Tanh''' || <math>\tanh(z) = \frac{e^z - e^{-z}}{e^z + e^{-z}}</math> || (−1, 1) || 以零为中心；对大输入仍会饱和 |- | '''ReLU''' || <math>\max(0, z)</math> || [0, ∞) || 现代网络的默认选择；可能导致"死神经元" |- | '''Leaky ReLU''' || <math>\max(\alpha z, z)</math>，其中 <math>\alpha > 0</math> 较小 || (−∞, ∞) || 解决死神经元问题 |- | '''Softmax''' || <math>\frac{e^{z_i}}{\sum_j e^{z_j}}</math> || (0, 1) || 用于多类分类的输出层 |} |