Search Results for author: Mark A. Horowitz

Found 1 papers, 1 papers with code

EIE: Efficient Inference Engine on Compressed Deep Neural Network

4 code implementations4 Feb 2016 Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark A. Horowitz, William J. Dally

EIE has a processing power of 102GOPS/s working directly on a compressed network, corresponding to 3TOPS/s on an uncompressed network, and processes FC layers of AlexNet at 1. 88x10^4 frames/sec with a power dissipation of only 600mW.

Cannot find the paper you are looking for? You can Submit a new open access paper.