Difference between revisions of "Capsule Networks (CapNets)"
| Line 12: | Line 12: | ||
* [http://papers.nips.cc/paper/6975-dynamic-routing-between-capsules.pdf Dynamic Routing Between Capsules | S. Sabour, N. Frosst, and G.E. Hinton] | * [http://papers.nips.cc/paper/6975-dynamic-routing-between-capsules.pdf Dynamic Routing Between Capsules | S. Sabour, N. Frosst, and G.E. Hinton] | ||
* [http://medium.com/ai%C2%B3-theory-practice-business/understanding-hintons-capsule-networks-part-i-intuition-b4b559d1159b Understanding Hinton’s Capsule Networks | Max Pechyonkin] | * [http://medium.com/ai%C2%B3-theory-practice-business/understanding-hintons-capsule-networks-part-i-intuition-b4b559d1159b Understanding Hinton’s Capsule Networks | Max Pechyonkin] | ||
| + | * [http://towardsdatascience.com/capsule-networks-the-new-deep-learning-network-bd917e6818e8 Capsule Networks: The New Deep Learning Network | Aryan Misra] | ||
Capsule is a nested set of neural layers. So in a regular neural network you keep on adding more layers. In CapsNet you would add more layers inside a single layer. Or in other words nest a neural layer inside another. The state of the neurons inside a capsule capture the above properties of one entity inside an image. A capsule outputs a vector to represent the existence of the entity. The orientation of the vector represents the properties of the entity. The vector is sent to all possible parents in the neural network. For each possible parent a capsule can find a prediction vector. Prediction vector is calculated based on multiplying it’s own weight and a weight matrix. Whichever parent has the largest scalar prediction vector product, increases the capsule bond. Rest of the parents decrease their bond. This routing by agreement method is superior than the current mechanism like max-pooling ([[Pooling / Sub-sampling: Max, Mean]]). [http://hackernoon.com/what-is-a-capsnet-or-capsule-network-2bfbe48769cc What is a CapsNet or Capsule Network? | Debarko De] | Capsule is a nested set of neural layers. So in a regular neural network you keep on adding more layers. In CapsNet you would add more layers inside a single layer. Or in other words nest a neural layer inside another. The state of the neurons inside a capsule capture the above properties of one entity inside an image. A capsule outputs a vector to represent the existence of the entity. The orientation of the vector represents the properties of the entity. The vector is sent to all possible parents in the neural network. For each possible parent a capsule can find a prediction vector. Prediction vector is calculated based on multiplying it’s own weight and a weight matrix. Whichever parent has the largest scalar prediction vector product, increases the capsule bond. Rest of the parents decrease their bond. This routing by agreement method is superior than the current mechanism like max-pooling ([[Pooling / Sub-sampling: Max, Mean]]). [http://hackernoon.com/what-is-a-capsnet-or-capsule-network-2bfbe48769cc What is a CapsNet or Capsule Network? | Debarko De] | ||
Revision as of 22:25, 6 February 2019
Youtube search... ...Google search
- Architectures
- Graph Convolutional Network (GCN), Graph Neural Networks (Graph Nets), Geometric Deep Learning
- Dynamic Routing Between Capsules | S. Sabour, N. Frosst, and G.E. Hinton
- Understanding Hinton’s Capsule Networks | Max Pechyonkin
- Capsule Networks: The New Deep Learning Network | Aryan Misra
Capsule is a nested set of neural layers. So in a regular neural network you keep on adding more layers. In CapsNet you would add more layers inside a single layer. Or in other words nest a neural layer inside another. The state of the neurons inside a capsule capture the above properties of one entity inside an image. A capsule outputs a vector to represent the existence of the entity. The orientation of the vector represents the properties of the entity. The vector is sent to all possible parents in the neural network. For each possible parent a capsule can find a prediction vector. Prediction vector is calculated based on multiplying it’s own weight and a weight matrix. Whichever parent has the largest scalar prediction vector product, increases the capsule bond. Rest of the parents decrease their bond. This routing by agreement method is superior than the current mechanism like max-pooling (Pooling / Sub-sampling: Max, Mean). What is a CapsNet or Capsule Network? | Debarko De
