Corpus ID: 15582471

A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman Encoding

@inproceedings{Han2015ADN,
  title={A Deep Neural Network Compression Pipeline: Pruning, Quantization, Huffman Encoding},
  author={Song Han and Huizi Mao and W. J. Dally},
  year={2015}
}

Song Han, Huizi Mao, W. J. Dally

Published 2015

Computer Science

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources. [...] Key Method Our method first prunes the network by learning only the important connections. Next, we quantize the weights to enforce weight sharing, finally, we apply Huffman encoding. After the first two steps we retrain the network to fine tune the remaining connections and the quantized centroids.Expand Abstract

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed