Deep Learning for Artificial Intelligence

Wednesday, January 11, 2017 - 15:00 to 15:50
703 Thackeray Hall
Speaker Information
Suren Jayasuriya
Postdoctoral Fellow
Carnegie Mellon University

Abstract or Additional Information

Abstract: Modern data science, image analysis, and natural language processing have recently flourished with the rise of deep
learning, a machine learning technique featuring neural networks. In this talk, we will describe the basics of deep learning and how it is used in modern artificial intelligence in image recognition/classification, object detection/tracking, and speech analysis. This talk will both address some of the mathematical foundations underlying these methods as well as the open theoretical challenges of analyzing these systems in practice. In addition, recent advances in using neural networks and game theory principles to generate new visual and audio content, such as computers that can paint or play music, will be highlighted. This talk will be accessible to undergraduate mathematics majors who have taken calculus, and all other concepts will be introduced as needed.

Bio: Suren Jayasuriya is a postdoctoral fellow at the Robotics Institute at Carnegie Mellon University. His research interests are in computational imaging, computer vision, and sensors. Before that, he obtained his PhD in Jan 2017 at Cornell University in ECE. He graduated from the University of Pittsburgh in 2012 with a B.S. in Mathematics and a B.A. in Philosophy. He received the NSF Graduate Research Fellowship in 2012, the Qualcomm Innovation Fellowship in 2015, and the Cornell ECE Outstanding PhD TA award in 2015.