arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1810.04041cs.CV
收藏

基于Capsule网络的学习和学习数据表示

On Learning and Learned Data Representation by Capsule Networks

Guangdong Polytechnic Normal University(广东技术师范大学);University of Technology Sydney(悉尼科技大学)

Ancheng Lin, Jun Li, Zhenyuan Ma

摘要:

在这项工作中,我们研究了以下内容:1)路由如何影响CapsNet模型拟合; 2)使用胶囊的表示如何帮助发现数据分布中的全局结构; 3)学习的数据表示如何适应和推广新任务。我们的研究得到了CapsNet的原始论文中提到的一些结果,它们是:1)路由操作决定了一层胶囊向上一层传递信息的确定性,而适当的确定性水平与模型适应度有关; 2)在使用具有已知2D结构的数据的设计实验中,胶囊表示实现了比标准卷积神经网络(CNN)中的神经元更有意义的2D流形嵌入,以及; 3)与标准CNN的神经元相比,连续层的胶囊耦合更少,并且更适应新的数据分布。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑