Please use this identifier to cite or link to this item: http://bura.brunel.ac.uk/handle/2438/23210
Title: no Routing Needed Between Capsules
Authors: Kalganova, T
Byerly, A
Dear, I
Keywords: capsules;convolutional Neural Network (CNN);homogeneous Vector Capsules (HVCs);MNIST
Issue Date: 19-Aug-2021
Publisher: Elsevier
Citation: Byerly, A., Kalganova, T. and Dear, I. (2021) 'No routing needed between capsules', Neurocomputing, 463, pp. 545-553. doi: 10.1016/j.neucom.2021.08.064.
Abstract: Copyright © 2021 The Authors. Most capsule network designs rely on traditional matrix multiplication between capsule layers and computationally expensive routing mechanisms to deal with the capsule dimensional entanglement that the matrix multiplication introduces. By using Homogeneous Vector Capsules (HVCs), which use element-wise multiplication rather than matrix multiplication, the dimensions of the capsules remain unentangled. In this work, we study HVCs as applied to the highly structured MNIST dataset in order to produce a direct comparison to the capsule research direction of Geoffrey Hinton, et al. In our study, we show that a simple convolutional neural network using HVCs performs as well as the prior best performing capsule network on MNIST using 5.5× fewer parameters, 4× fewer training epochs, no reconstruction sub-network, and requiring no routing mechanism. The addition of multiple classification branches to the network establishes a new state of the art for the MNIST dataset with an accuracy of 99.87% for an ensemble of these models, as well as establishing a new state of the art for a single model (99.83% accurate).
URI: https://bura.brunel.ac.uk/handle/2438/23210
DOI: https://doi.org/10.1016/j.neucom.2021.08.064
ISSN: 0925-2312
Appears in Collections:Dept of Electronic and Electrical Engineering Research Papers

Files in This Item:
File Description SizeFormat 
FullText.pdf1.68 MBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons