@article{deepcompressioncompressingdeepneural, title = {Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding}, author = {Song Han and Huizi Mao and William J. Dally}, year = {2015}, eprint = {1510.00149}, archivePrefix = {arXiv}, url = {http://arxiv.org/abs/1510.00149v5}, }