Existing high-performance deep learning models require very intensive computing. For this reason, it is difficult to embed a deep learning model into a system with limited resources. In this paper, we propose the novel idea of the network compression as a method to solve this limitation. The principle of this idea is to make iterative pruning more effective and sophisticated by simulating the reduced network. A simple experiment was conducted to evaluate the method; the results showed that the proposed method achieved higher performance than existing methods at the same pruning level.
@article{arxiv.1902.04224,
title = {Effective Network Compression Using Simulation-Guided Iterative Pruning},
author = {Dae-Woong Jeong and Jaehun Kim and Youngseok Kim and Tae-Ho Kim and Myungsu Chae},
journal= {arXiv preprint arXiv:1902.04224},
year = {2019}
}