We started off the chapter by understanding what k-shot learning is. We learned that in n-way k-shot learning, n-way implies the number of classes we have in our dataset and k-shot implies the number of data points we have in each class; and support set and the query set are equivalent to the train and test sets. Then we explored siamese networks. We learned how siamese networks use an identical network to learn the similarity of two inputs.

Followed by this, we learned about prototypical networks, which create a prototypical representation of each class and classify a query point (a new point) based on the distance between the class prototype and the query point. We also learned how relation networks use two different functions embedding and relation function to classify an image.

At the end of the chapter, we learned about matching networks and how it uses different embedding functions for the support set and the query set to classify an image.

Deep learning is one of the most interesting branches in the field of AI. Now that you've understood various deep learning algorithms, you can start building deep learning models and create interesting applications and also contribute to deep learning research.