IEEE Style Citation: Anusha Mehta, V. D. Parmar, “A Study on Capsule Networks with the Comparative Analysis of Capsule Networks and CNN,” International Journal of Computer Sciences and Engineering, Vol.7, Issue.4, pp.105-108, 2019.
MLA Style Citation: Anusha Mehta, V. D. Parmar "A Study on Capsule Networks with the Comparative Analysis of Capsule Networks and CNN." International Journal of Computer Sciences and Engineering 7.4 (2019): 105-108.
APA Style Citation: Anusha Mehta, V. D. Parmar, (2019). A Study on Capsule Networks with the Comparative Analysis of Capsule Networks and CNN. International Journal of Computer Sciences and Engineering, 7(4), 105-108.
BibTex Style Citation:
@article{Mehta_2019,
author = {Anusha Mehta, V. D. Parmar},
title = {A Study on Capsule Networks with the Comparative Analysis of Capsule Networks and CNN},
journal = {International Journal of Computer Sciences and Engineering},
issue_date = {4 2019},
volume = {7},
Issue = {4},
month = {4},
year = {2019},
issn = {2347-2693},
pages = {105-108},
url = {https://www.ijcseonline.org/full_paper_view.php?paper_id=4002},
doi = {https://doi.org/10.26438/ijcse/v7i4.105108}
publisher = {IJCSE, Indore, INDIA},
}
RIS Style Citation:
TY - JOUR
DO = {https://doi.org/10.26438/ijcse/v7i4.105108}
UR - https://www.ijcseonline.org/full_paper_view.php?paper_id=4002
TI - A Study on Capsule Networks with the Comparative Analysis of Capsule Networks and CNN
T2 - International Journal of Computer Sciences and Engineering
AU - Anusha Mehta, V. D. Parmar
PY - 2019
DA - 2019/04/30
PB - IJCSE, Indore, INDIA
SP - 105-108
IS - 4
VL - 7
SN - 2347-2693
ER -
VIEWS
PDF
XML
632
372 downloads
200 downloads
Abstract
Artificial intelligence, with the emergence of machine learning and deep learning techniques, is growing up with breath neck speed. With the evaluation of the deep convolutional neural network, applications like image classification, object recognition and detection become easier. Recently, a new network deep learning architecture named Capsule Network is introduced to overcome some spatial and rotational limitations of CNN by using the concepts of capsules and the dynamic routing algorithm. Capsules are a group of neurons that generates activity vector whose length predicts the class of image and the orientation defines the pose parameters related to the image. Capsule networks have resulted in state of the art performance on various dataset such as MNIST. The paper defines the architecture and working of the capsule network, along with the comparative analysis of CNN and Capsule network on the various dataset. Along with this, the paper specifies the hands-on experiments done on capsule networks and the future scope with capsule networks.
[1] K. O`Shea, R. Nash. "An introduction to convolutional neural networks." arXiv preprint arXiv:1511.08458 (2015).
[2] S. Sabour, N. Frosst, and GE. Hinton. "Dynamic routing between capsules." In the Proceedings of 2017 NIPS Conference on Advances in neural information processing systems, pp. 3856-3866. 2017.
[3] GE. Hinton, A. Krizhevsky, SD. Wang. "Transforming auto-encoders." In International Conference on Artificial Neural Networks, Springer, Berlin, Heidelberg, pp. 44-51, 2011.
[4] GE. Hinton, S. Sabour, N. Frosst. "Matrix capsules with EM routing." Open review (2018).
[5] P. Nair, R. Doshi, S. Keselj. "Pushing the limits of capsule networks." Technical note (2018).
[6] R. LaLonde, U. Bagci. "Capsules for object segmentation." arXiv preprint arXiv:1804.04241 (2018).
[7] M. Engelin. "CapsNet Comprehension of Objects in Different Rotational Views: A comparative study of capsule and convolutional networks." (2018).
[8] A. Gulli, and S.Pal. “Deep Learning with Keras”. Packt Publishing Ltd, Birmingham - Mumbai, pp. 71-105, 2017.
VIEWS
PDF 
XML 
