An Enhanced Deep Neural Network for Predicting Workplace Absenteeism

Figure 2

Shallow Neural Network is created when Logistic Regression is applied multiple times. We also show the forward propagation to compute loss and backward propagation to update hyperparameters , , , and . The forward propagation and backward propagation are performed for a number of iterations, until we reach to the global minima of the sum of cross-entropy loss for all features.