papers AI Learner
The Github is limit! Click to go to the new site.

On Learning and Learned Representation by Capsule Networks

2019-04-25
Ancheng Lin, Jun Li, Zhenyuan Ma

Abstract

In this work, we investigate the following: 1) how the routing affects the CapsNet model fitting; 2) how the representation using capsules helps discover global structures in data distribution, and; 3) how the learned data representation adapts and generalizes to new tasks. Our investigation yielded the results some of which have been mentioned in the original paper of CapsNet, they are: 1) the routing operation determines the certainty with which a layer of capsules pass information to the layer above and the appropriate level of certainty is related to the model fitness; 2) in a designed experiment using data with a known 2D structure, capsule representations enable a more meaningful 2D manifold embedding than neurons do in a standard convolutional neural network (CNN), and; 3) compared with neurons of the standard CNN, capsules of successive layers are less coupled and more adaptive to new data distribution.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1810.04041

PDF

http://arxiv.org/pdf/1810.04041


Similar Posts

Comments