English

Fast Exploration of Weight Sharing Opportunities for CNN Compression

Machine Learning 2021-02-03 v1 Artificial Intelligence Computer Vision and Pattern Recognition Neural and Evolutionary Computing

Abstract

The computational workload involved in Convolutional Neural Networks (CNNs) is typically out of reach for low-power embedded devices. There are a large number of approximation techniques to address this problem. These methods have hyper-parameters that need to be optimized for each CNNs using design space exploration (DSE). The goal of this work is to demonstrate that the DSE phase time can easily explode for state of the art CNN. We thus propose the use of an optimized exploration process to drastically reduce the exploration time without sacrificing the quality of the output.

Keywords

Cite

@article{arxiv.2102.01345,
  title  = {Fast Exploration of Weight Sharing Opportunities for CNN Compression},
  author = {Etienne Dupuis and David Novo and Ian O'Connor and Alberto Bosio},
  journal= {arXiv preprint arXiv:2102.01345},
  year   = {2021}
}

Comments

Presented at DATE Friday Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures (SLOHA 2021) (arXiv:2102.00818)