"On-device Machine Learning: small models and fast prediction"

Si Si, Researcher and Software Engineer, Google Research

March 12th (Monday), 11:00am
Harold Frank Hall (HFH), Rm. 4164 (ECE Conf. Rm.)

Many complex machine learning models have demonstrated tremendous success for massive data. However, these advances are not necessarily feasible when deploying these models to devices due to large model size and evaluation cost. In many real-world applications such as robotics, self-driving car, and smartphone apps, the learning tasks need to be carried out in a timely fashion on a computation and memory limited platform. Therefore, it is extremely important to study building “small” models from “big” machine learning models. The main topic of my talk is to investigate how to reduce the model size and speed up the elevation for complex machine learning models while maintaining similar accuracy. Specifically, I will discuss how to compress the model and achieve fast prediction for different real-world machine learning applications including matrix approximation and extreme classification.

About Si Si:

Photo of Si Si Si Si is a researcher and software engineer in Google research. Her research focus is developing scalable machine learning models. Si obtained her bachelor's degree from the University of Science and Technology of China in 2008, M.Phil. degree in 2010 from University of Hong Kong, and Ph.D. from University of Texas at Austin in 2016. She is the recipient of the MCD fellowship in 2010-2013, and the best paper award in ICDM 2012. Si is selected as one of the Rising Stars in EECS 2017.

Hosted by: UCSB CE Program