Translations:Softmax Function/30/en

1. A neural network produces raw logits $ \mathbf{z} $ from its final linear layer.
2. Softmax converts logits to probabilities: $ \hat{\mathbf{y}} = \sigma(\mathbf{z}) $.
3. The predicted class is $ \hat{c} = \arg\max_k \hat{y}_k $.
4. Training uses Cross-Entropy Loss applied to the predicted distribution and the true labels.