Automated Perception in the Real World: The Problem of Scarce Data
|Event Date:||October 11, 2018|
|Speaker:||Jan Ernst, Ph.D|
|Speaker Affiliation:||Siemens Corporate Technology|
|School or Program:||Electrical and Computer Engineering
Jan Ernst, Ph.D.
Siemens Corporate Technology
Machine perception is a key step towards artificial intelligence in domains such as self-driving cars, industrial automation, and robotics. Much progress has been made in the past decade, driven by machine learning, ever-increasing computational power, and the reliance on (seemingly) vast data sets. There are however critical issues in translating academic progress into the real world: available data sets may not match real world environments well, and even if they are abundant and matching well, then interesting samples from a real world perspective may be exceedingly rare and thus still be too sparsely represented to learn from directly. In this talk I illustrate how we have approached this problem strategically as an example of industrial R&D from inception to product. I will also go in depth on an approach to automatically infer previously unseen data by learning compositional visual concepts via mutual cycle consistency.
Dr. Jan Ernst is Principal Scientist at Siemens Corporate Technology in Princeton, NJ. He received a Ph.D. degree from University of Erlangen-Nuremberg in Erlangen, Germany. He has 20 years of industrial R&D experience in the field of computer vision and machine learning. Before becoming Principal Scientist, Dr. Ernst has been in the positions of Director of Research Group and Project Manager at Siemens. He is a certified R&D Project Management Professional.
Jeff Siskind, firstname.lastname@example.org, 49-63197