Details
Presenter(s)
![Islam Eldifrawi Headshot](https://confcats-catavault.s3.amazonaws.com/CATAVault/ieeecass/master/files/styles/cc_user_photo/s3/user-pictures/21361_0.jpg?h=ad27ff84&itok=gXQ-ZmWG)
Display Name
Islam Eldifrawi
- Affiliation
-
AffiliationEgypt-Japan University of Science & Technology
- Country
-
CountryEgypt
Abstract
Deep Capsule Networks achieved state-of-the-art accuracy on CIFAR10. Despite all these accomplishments, Deep Capsule Networks are very slow. In this paper, Deep Fast Embedded Capsule Net-work (Deep-FECapsNet) is introduced. Deep-FECapsNet is a novel deep capsule network architecture that uses 1D convolution based dynamic routing with a fast element-wise multiplication transformation process. It competes with the state-of-the-art methods in terms of accuracy in the capsule domain, and also excels in terms of speed, and reduced complexity. This is shown by the 58% reduction in the number of trainable parameters and 64% reduction in the average epoch time in the training process.