Which loss function is the standard choice for training a neural network for multi-class classification with a Softmax output layer?
Show answer
Categorical Cross-Entropy
Cross-entropy measures the performance of a classification model whose output is a probability value between 0 and 1. It penalizes predictions that are confident but wrong, aligning well with maximum likelihood estimation.
Also asked as:
- For a multi-class classification neural network using Softmax, what is the standard loss function used for training?