What do you mean by Capsule Neural Network?

Ans: Capsule is a nested set of neural layers. In a regular neural network, you keep on adding more layers where as in Capsule Neural Network you would add more layers inside a single layer. In other words, nest a neural layer inside another layer. A capsule Neural Network gives output a vector to represent the presence of the entity. The direction of the vector represents the properties of the entity. This vector is sent to all possible parents in the neural network. For each possible parent a capsule can find out the prediction vector.

Prediction vector is calculation based on multiplying its own weight and a weight matrix. Parent which has the largest scalar prediction vector product, increases the capsule bond. Rest of the parents decrease their bond. Instead of extracting a feature with a specific variant, a capsule is trained to extract the likeliness of a feature and its variant. So, the purpose of the capsule is not only to detect a feature but also trains the model to learn the variant.