Data Center Group
Zhenlin is a Deep Learning Data Scientist at Intel. He started working on AI project for deep learning model acceleration on Xeon platform. His earlier work include MKL-DNN support and integration on Mxnet, CNTK and TF for CNN, RNN and recommendation models and quantization research on recommendation and voice recognition systems. He now work on auto quantization tool for Intel DLBoost technology.
Most inference applications today require low latency, high memory bandwidth, and large compute capacity. With the increasing use and growing…