Search Results for author: Gursharan Sandhu

Found 2 papers, 0 papers with code

Fast Inference in Capsule Networks Using Accumulated Routing Coefficients

no code implementations15 Apr 2019 Zhen Zhao, Ashley Kleinhans, Gursharan Sandhu, Ishan Patel, K. P. Unnikrishnan

Afterward, the routing coefficients associated with the training examples are accumulated offline and used to create a set of "master" routing coefficients.

Object Rotated MNIST

Capsule Networks with Max-Min Normalization

no code implementations22 Mar 2019 Zhen Zhao, Ashley Kleinhans, Gursharan Sandhu, Ishan Patel, K. P. Unnikrishnan

Capsule Networks (CapsNet) use the Softmax function to convert the logits of the routing coefficients into a set of normalized values that signify the assignment probabilities between capsules in adjacent layers.

Cannot find the paper you are looking for? You can Submit a new open access paper.