In this chapter, we will cover the following recipes:

• Training a vanilla neural network
• Scaling the input dataset
• Impact of training when the majority of inputs are greater than zero
• Impact of batch size on model accuracy
• Building a deep neural network to improve network accuracy
• Varying the learning rate to improve network accuracy
• Varying the loss optimizer to improve network accuracy
• Understanding the scenario of overfitting
• Speeding up the training process using batch normalization

In the previous chapter, we looked at the basics of the function of a neural network. We also learned that there are various hyperparameters that impact the accuracy of a neural network. In this chapter, we will get into the details of the functions of the various hyperparameters within a neural network.

All the codes for this chapter are available at https://github.com/kishore-ayyadevara/Neural-Networks-with-Keras-Cookbook/blob/master/Neural_network_hyper_parameters.ipynb