“ Network Management Unit (NMU): A Network Interface Architecture for Job-Level Protection Domains” CVA Technical Report 133, October 2013. Dally, Kurt Keutzerĭistributed Systems Publications Distributed Systems Technical Reports SqueezeNet: AlexNet-Level Accuracy with 50x Fewer Parameters and < 0.5MB Model Sizeįorrest Iandola, Song Han, Matthew Moskewicz, Khalid Ashraf, William J. International Conference on Learning Representations (ICLR), April 2017. Song Han, Jeff Pool, Sharan Narang, Huizi Mao, Shijian Tang, Erich Elsen, Bryan Catanzaro, John Tran, William J. DallyĪdvances in Neural Information Processing Systems (NIPS), December 2015.ĭSD: Dense-Sparse-Dense Training for Deep Neural Networks Song Han, Jeff Pool, John Tran, William J. Learning both Weights and Connections for Efficient Neural Networks International Conference on Learning Representations (ICLR), May 2016, Best Paper Award. NIPS Deep Learning Symposium, December 2015. International Symposium on Computer Architecture (ISCA), June 2016 Hotchips, Aug 2016.ĭeep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark Horowitz, William J. Click on the Section of the page you would like toĮIE: Efficient Inference Engine on Compressed Deep Neural Network This is a partial list of the publications by the Stanford Concurrent VLSI Architecture group organized by project.