Hands-On Meta Learning with Python

Architecture of siamese networks

Now that we have a basic understanding of siamese networks, we will explore them in detail. The architecture of a siamese network is shown in the following diagram:

As you can see in the preceding diagram, a siamese network consists of two identical networks both sharing the same weights and architecture. Let's say we have two inputs, X₁ and X₂. We feed our input X₁ to Network A, that is, f_w(X₁), and we feed our input X₂ to Network B, that is, f_w(X₂). As you will notice, both of these networks have the same weights, w, and they will generate embeddings for our input, X₁ and X₂. Then, we feed these embeddings ...