All translations

Enter a message name below to show all available translations.

Found 3 translations.

Name	Current message text
^h English (en)	# A neural network produces raw {{Term\|logits}} <math>\mathbf{z}</math> from its final linear layer. # Softmax converts {{Term\|logits}} to probabilities: <math>\hat{\mathbf{y}} = \sigma(\mathbf{z})</math>. # The predicted class is <math>\hat{c} = \arg\max_k \hat{y}_k</math>. # Training uses [[Cross-Entropy Loss]] applied to the predicted distribution and the true labels.
^h Spanish (es)	# Una red neuronal produce {{Term\|logits}} brutos <math>\mathbf{z}</math> a partir de su capa lineal final. # Softmax convierte los {{Term\|logits}} en probabilidades: <math>\hat{\mathbf{y}} = \sigma(\mathbf{z})</math>. # La clase predicha es <math>\hat{c} = \arg\max_k \hat{y}_k</math>. # El entrenamiento usa [[Cross-Entropy Loss]] aplicada a la distribución predicha y a las etiquetas verdaderas.
^h Chinese (zh)	# 神经网络通过其最后的线性层产生原始的 {{Term\|logits}} <math>\mathbf{z}</math>。 # Softmax 将 {{Term\|logits}} 转换为概率：<math>\hat{\mathbf{y}} = \sigma(\mathbf{z})</math>。 # 预测的类别为 <math>\hat{c} = \arg\max_k \hat{y}_k</math>。 # 训练使用应用于预测分布与真实标签的 [[Cross-Entropy Loss]]。