Slide 28
Slide 28 text
! モデル圧縮で透かしが消えるか?
" lossless : Huffman cording [5]
" lossy : weight quantization[5, 6], parameter pruning [5, 6]
Robustness: model compression
[5] S. Han, H. Mao, and W. J. Dally. Deep compression: Compressing deep neural networks with pruning, trained
quantization and huffman coding. In Proc. of ICLR, 2016.
[6] S. Han, J. Pool, J. Tran, and W. J. Dally. Learning both weights and connections for efficient neural networks.
In Proc. of NIPS, 2015.