QCon San Francisco 2021 November 1-5, 2021 | | Machine Learning for Handwriting and Sketch Recognition

Abstract

The terms “big data”, “machine learning”, “neural networks”, and “deep learning” have appeared in many attention-grabbing headlines over the years, but what do they really mean? This presentation will describe some concrete examples of how they have impacted a variety of products, by enabling computers to interact with the world as people do, rather than the other way around. We then take a deeper dive into how machine learning and neural networks are used in two particular products, recognition of handwriting and sketches. Finally, we look at how the “big data” obtained from a sketch recognition game can not only be used for machine learning, but to learn more about how people around the world understand and draw everyday objects.

Speaker: Li-Lun Wang

Software Engineer @Google

Li-Lun Wang received his BS degree in Computer Science and Information Engineer from National Taiwan University in 2002, and PhD in Computer Science from University of Illinois at Urbana-Champaign in 2012. He joined Google Research in 2012, working on handwriting recognition. His research interests include artificial intelligence and machine learning.

Find Li-Lun Wang at

Speaker page

https://www.linkedin.com/in/li-lun-wang-6b32263/

Speaker: Henry Rowley

Staff Research Scientist @Google

Henry A. Rowley received BS degrees in Electrical Engineering and Computer Science from the University of Minnesota in 1992, a Masters in Computer Science from Carnegie Mellon University in 1994, and PhD in Computer Science from Carnegie Mellon University in 1999 for his thesis work on neural network-based face detection. After graduating he worked at Zaxel Systems, Inc. on lossless video compression and multi-view stereo reconstruction, and at Microsoft on Chinese, Japanese, and Korean handwriting recognition. Currently he is a member of the Google Research group, where he has worked on computer vision, machine learning, and most recently handwriting recognition.