neural network loss function criterion
Deep Neural Network Loss Function Criterions
In our deep learning model, depending on whether we are doing classification or regression tasks, we have to define a loss function that compares the predicted result vs the expected result (labeled data). In classification problems, the loss function calculates the loss for misclassifications. Cross-Entropy Loss measures the performance of classification. It is a combination of the Negative Log-Likelihood Loss (NLL) and Softmax. Some of the most used loss functions for regression tasks are L1 loss, MSE (L2 loss), and Smooth L1 Loss.