Capsule network

What is capsule network?
A capsule network is a kind of shorthand for a specific type of neural network pioneered by Stanford scientist Geoffrey Hinton. In the capsule network, a specific methodology is applied to image processing in order to try to influence the understanding of objects from a three-dimensional spectrum.

To understand capsule networks, or what Hinton called the 'dynamic inter-capsule routing' algorithm, it is important to understand convolutional neural networks (CNNs). Convolutional neural networks have done an amazing job helping computers put together features in image processing to understand images the same way humans do. Complex filtering, pooling and scaling layers help to achieve detailed results. But CNNs are not good at understanding an image from different three-dimensional views.

Hinton's concept is that algorithms like dynamic routing between capsules can use reverse rendering to decompose objects and understand the relationships of their views from different three-dimensional angles. Experts point out that advances in computing power and data storage have made items like capsule networks possible. These interesting ideas form the basis for current groundbreaking research on powerful AI.

Was the explanation to "Capsule network"Helpful? Rate now:

Synonym für / Anderes Wort für

  • kapsel netzwerk

Weitere Erklärungen zu Anfangsbuchstabe C