English

Efficient Hardware Realization of Convolutional Neural Networks using Intra-Kernel Regular Pruning

Computer Vision and Pattern Recognition 2018-03-19 v1

Abstract

The recent trend toward increasingly deep convolutional neural networks (CNNs) leads to a higher demand of computational power and memory storage. Consequently, the deployment of CNNs in hardware has become more challenging. In this paper, we propose an Intra-Kernel Regular (IKR) pruning scheme to reduce the size and computational complexity of the CNNs by removing redundant weights at a fine-grained level. Unlike other pruning methods such as Fine-Grained pruning, IKR pruning maintains regular kernel structures that are exploitable in a hardware accelerator. Experimental results demonstrate up to 10x parameter reduction and 7x computational reduction at a cost of less than 1% degradation in accuracy versus the un-pruned case.

Keywords

Cite

@article{arxiv.1803.05909,
  title  = {Efficient Hardware Realization of Convolutional Neural Networks using Intra-Kernel Regular Pruning},
  author = {Maurice Yang and Mahmoud Faraj and Assem Hussein and Vincent Gaudet},
  journal= {arXiv preprint arXiv:1803.05909},
  year   = {2018}
}

Comments

6 pages, 8 figures, ISMVL 2018

R2 v1 2026-06-23T00:54:39.798Z