In this chapter, we have learned what siamese networks are and how to build face and audio recognition models using siamese networks. We explored the architecture of siamese networks, which basically consists of two identical neural networks both having the same weights and architecture and the output of these networks is plugged into some energy function to understand the similarity.

In the next chapter, we will learn about prototypical networks and the variants of the same, such as Gaussian prototypical and semi prototypical networks. We will also see how to use prototypical networks for omniglot character set classification.