Dr. Cheng received her B.S from University of Science and Technology of China in 2005 and then her Ph.D. in Physics from University of California, Irvine in 2011, with her Ph.D. work focusing on spin transfer torque and stochastic resonance in magnetic systems. She then moved to Silicon Valley to first work in HGST, a Western Digital company, as a principle engineer in charge of read head product design in hard disk drive. Around 2014, she developed strong interest in data analysis and machine learning and then joined Amazon Lab126 as a research scientist. Her current job function is to explore new technology for developing scientific testing and specifications, and to apply statistical prediction and machine learning in data analysis for consumer electronics.

Abstract
With the rapid development of big data and cloud computation techniques and resources, the boundary between hardware and software has diminished. The talk begins with a simple introduction to machine learning and data analysis, and an illustrative explanation of K-means clustering algorithm, one of the most commonly used unsupervised learning algorithm. The speaker will then go through several case studies on applying machine learning techniques on consumer data analysis to improve hardware design and automate reliability testing. Collecting and mining field data has great impact to quality, cost and consumer perception in the whole product development process, from concept to ship. The talk will end up with some fun videos demonstrating reliability testing in consumer electronics industry.

主办：中科院物理所技术部电子学仪器部
邀请人：郇 庆 联系电话：82649096
E-mail: ts01service@iphy.ac.cn