BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Towards Global\, General-Purpose Geographic Location Encoders - Ko
 nstantin Klemmer\, Microsoft Research
DTSTART:20240328T130000Z
DTEND:20240328T140000Z
UID:TALK211927@talks.cam.ac.uk
CONTACT:114742
DESCRIPTION:\n\nGeospatial data is common across a wide range of disciplin
 es and modeling tasks\, e.g. in ecology or urban analytics. Location featu
 res are often not readily available and need to be obtained via individual
  data collection and fusion. This opens the opportunity for a new class of
  "foundation models": global\, general-purpose geographic location encoder
 s\, which provide vector embeddings summarizing the characteristics of a l
 ocation for convenient usage in downstream tasks. I will outline the intui
 tion and technical challenges for building these models\, and contextualiz
 e them with respect to other geospatial foundation models in the vision\, 
 language and geophysical domain.\n\nBio:\n\nI am a postdoctoral researcher
  at Microsoft Research New England and part of the Machine Learning and St
 atistics group. My research focuses on the representation of geographic ph
 enomena in machine learning methods\, particularly in neural networks. My 
 recent work includes the integration of notions of spatial dependency into
  neural networks and the unsupervised training of location encoders that l
 earn characteristics of a given location and can be deployed in different 
 downstream tasks. My work is motivated by real-world challenges such as cl
 imate change and increasing urbanisation\, combining technical and methodo
 logical research with application and deployment studies. I have a PhD in 
 Computer Science and Urban Science from the University of Warwick and spen
 t time as a visiting student at NYU\, as an Enrichment student at the Alan
  Turing Institute and as a Beyond Fellow at TUM and DLR.  
LOCATION:FW11\, William Gates Building. Zoom link: https://cl-cam-ac-uk.zo
 om.us/j/4361570789?pwd=Nkl2T3ZLaTZwRm05bzRTOUUxY3Q4QT09&amp\;from=addon 
END:VEVENT
END:VCALENDAR
