Zero-skipping in CapsNet. Is it worth it?

7 pages•Published: March 9, 2020

Ramin Sharifi, Pouya Shiri and Amirali Baniasadi

Abstract

Capsule networks (CapsNet) are the next generation of neural networks. CapsNet can be used for classification of data of different types. Today’s General Purpose Graphical Processing Units (GPGPUs) are more capable than before and let us train these complex networks. However, time and energy consumption remains a challenge. In this work, we investigate if skipping trivial operations i.e. multiplication by zero in CapsNet, can possibly save energy. We base our analysis on the number of multiplications by zero detected while training CapsNet on MNIST and Fashion- MNIST datasets.

Keyphrases: capsule networks, trivial operations, zero skipping

In: Gordon Lee and Ying Jin (editors). Proceedings of 35th International Conference on Computers and Their Applications, vol 69, pages 355-361.

Links:	https://easychair.org/publications/paper/f99W
	https://doi.org/10.29007/cd8h

BibTeX entry

@inproceedings{CATA2020:Zero_skipping_CapsNet._Is,
  author    = {Ramin Sharifi and Pouya Shiri and Amirali Baniasadi},
  title     = {Zero-skipping in CapsNet. Is it worth it?},
  booktitle = {Proceedings of 35th International Conference on Computers and Their Applications},
  editor    = {Gordon Lee and Ying Jin},
  series    = {EPiC Series in Computing},
  volume    = {69},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {/publications/paper/f99W},
  doi       = {10.29007/cd8h},
  pages     = {355-361},
  year      = {2020}}

Download PDF Open PDF in browser