Main content

Interpreting Capsule Networks for Classification by Routing Path Visualization

Show full item record

Title: Interpreting Capsule Networks for Classification by Routing Path Visualization
Author: Bhullar, Aman
Department: Department of Mathematics and Statistics
Program: Mathematics and Statistics
Advisor: Ayesha, Ali
Abstract: gradrec1@uoguelph.cAutomating the classification of images is difficult in specialized areas because often there is insufficient labeled data to train a convolutional neural network, the most popular model for image classification [11]. Capsule networks, a neural network architecture proposed for image classification by Sabour et al. 2017, have been shown to require a smaller dataset than convolutional neural networks to train well [14]. In this thesis, a capsule network model that can classify astronomical images as containing or not containing at least one supernova light echo is identified, and shown to obtain an accuracy of 90% on the test set. In addition, routing path visualization, a technique for interpreting the entity that a given capsule in a capsule networks detects, is introduced in this thesis. Experimental results demonstrate that routing path visualization can also be used to precisely localize supernova light echoes in astronomical images.
URI: http://hdl.handle.net/10214/17834
Date: 2020-03-17
Rights: Attribution 4.0 International
Terms of Use: All items in the Atrium are protected by copyright with all rights reserved unless otherwise indicated.


Files in this item

Files Size Format View
Bhullar_Aman_202003_Msc.pdf 3.974Mb PDF View/Open

This item appears in the following Collection(s)

Show full item record

Attribution 4.0 International Except where otherwise noted, this item's license is described as Attribution 4.0 International