报告题目：A Gentle Introduction on Deep Learning and Its Applications

报告人：俞栋主任研究员（微软专家雷蒙德研究院），黄美玉高级研究员（微软苏州研究院）

时间：2014年5月30日（星期五）9:30

地点：天赐庄校区理工大楼504室

报告摘要：In this short tutorial I will introduce deep learning and its brief history and core concepts. I will discuss how to apply deep learning to attack your own problems using speech recognition, image classification, and natural language understanding as examples. I will then explain why deep learning works for these tasks. I will conclude the tutorial with some research topics on using deep learning for speech recognition and natural language understanding.

报告人简介：Dr. Dong Yu is a principal researcher at the Microsoft speech and dialog research group. His research interests include speech processing, robust speech recognition, discriminative training, and machine learning. He has published over 130 papers in these areas and is the co-inventor of more than 50 granted/pending patents. His most recent work on the context-dependent deep neural network hidden Markov model (CD-DNN-HMM), which was recognized by the IEEE SPS 2013 best paper award, has been seriously challenging the dominant position of the conventional GMM based system for large vocabulary speech recognition.

Dr. Mei-Yuh Huang receives her PhD in Computer Science from Carnegie Mellon University in 1994. She
worked at Microsoft in Redmond, USA, from 1994-2004 and 2008-2012, with four years in between at
University of Washington. Since November 2012, she has returned to China and am leading the speech
recognition and natural language understanding efforts for Microsoft in China. Her interests lie in speech recognition, machine translation, and natural language understanding. She has published dozens of journal and conference papers, and serves as an associated editor for IEEE Transactions on Audio, Speech
and Language Processing. She is an IEEE senior member.