This chapter gives an overview of the techniques for training a deep neural network. Here, we briefly discuss
How learned information flows through a neural network
The role of the cost function at the output layer of the network
One-hot encoding and the softmax activation function for determining class membership at the output layer of a classification problem
The backpropagation algorithm for improving the learned parameters of the network
Activation functions that enable the neural network to learn non-linear patterns
In this chapter, ...
