Show simple item record

dc.contributor.authorErnst, Jan
dc.date.accessioned2018-12-06T17:18:25Z
dc.date.available2018-12-06T17:18:25Z
dc.date.issued2018-11-30
dc.identifier.urihttp://hdl.handle.net/1853/60592
dc.descriptionPresented on November 30, 2018 at 2:30 p.m. in the Marcus Nanotechnology Building, Room 1116.en_US
dc.descriptionJan Ernst is the Principal Scientist at Siemens Corporate Technology in Princeton, NJ.en_US
dc.descriptionRuntime: 52:15 minutesen_US
dc.description.abstractMachine perception is a key step toward 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.en_US
dc.format.extent52:15 minutes
dc.language.isoen_USen_US
dc.relation.ispartofseriesMachine Learning@Georgia Tech Seminar Seriesen_US
dc.subjectAugmentationen_US
dc.subjectData scarcityen_US
dc.titleAutomated Perception in the Real World: The Problem of Scarce Dataen_US
dc.typeLectureen_US
dc.typeVideoen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Machine Learningen_US
dc.contributor.corporatenameSiemens Researchen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record