This chapter will focus on understanding the various architectures present today in deep learning. A lot of the success of neural networks lies in the careful design of the neural network architecture. We have come a long way since the traditional Artificial Neural Networks (ANNs) of the 1960s. In this book, essential model architectures such as fully connected deep neural networks, Convolutional Neural Networks (CNNs), recurrent neural networks (RNNs), Long Short-Term Memory (LSTM) networks, and the most recent capsule networks will be covered.

In this chapter, we will cover the following topics:

• Why neural network architecture design is important
• Various popular architecture designs and applications