TY - JOUR
AU - Zhang, Yi
AB -  KDD 2017 Applied Data Science Paper KDD ™17, August 13 “17, 2017, Halifax, NS, Canada Deep Embedding Forest: Forest-based Serving with Deep Embedding Features Jie Zhu Bing Ads of AI & Research Group Microsoft Corporation One Microsoft Way Redmond, WA 98052-6399 Dong Yu Microsoft Research Microsoft Corporation One Microsoft Way Redmond, WA 98052-6399 Ying Shan Bing Ads of AI & Research Group Microsoft Corporation One Microsoft Way Redmond, WA 98052-6399 Holakou Rahmanian Department of Computer Science University of California Santa Cruz 1156 High St Santa Cruz, CA 95064 JC Mao Bing Ads of AI & Research Group Microsoft Corporation One Microsoft Way Redmond, WA 98052-6399 Yi Zhang Bing Ads of AI & Research Group Microsoft Corporation One Microsoft Way Redmond, WA 98052-6399 ABSTRACT CCS CONCEPTS Deep Neural Networks (DNN) have demonstrated superior ability to extract high level embedding vectors from low level features. Despite the success, the serving time is still the bottleneck due to expensive run-time computation of multiple layers of dense matrices. GPGPU, FPGA, or ASIC-based serving systems require additional hardware that are not in the mainstream design of most commercial applications. In contrast, tree or forest-based models are widely adopted because of low serving cost, 
TI - Deep Embedding Forest: Forest-based Serving with Deep Embedding Features
DA - 2017-08-13
UR - https://www.deepdyve.com/lp/association-for-computing-machinery/deep-embedding-forest-forest-based-serving-with-deep-embedding-kMTP3as1pi
DP - DeepDyve
ER -