PropertyValue
?:abstract
  • We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of discrete events that are localized in continuous time and space. Central to our approach is a combination of recurrent continuous-time neural networks with two novel neural architectures, i.e., Jump and Attentive Continuous-time Normalizing Flows. This approach allows us to learn complex distributions for both the spatial and temporal domain and to condition non-trivially on the observed event history. We validate our models on data sets from a wide variety of contexts such as seismology, epidemiology, urban mobility, and neuroscience.
is ?:annotates of
?:arxiv_id
  • 2011.04583
?:creator
?:externalLink
?:license
  • arxiv
?:pdf_json_files
  • document_parses/pdf_json/289322a72c5693f5942054019a8e90bd3adebd94.json
?:publication_isRelatedTo_Disease
?:sha_id
?:source
  • ArXiv
?:title
  • Neural Spatio-Temporal Point Processes
?:type
?:year
  • 2020-11-09

Metadata

Anon_0  
<http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://purl.org/net/provenance/ns#DataItem>
<http://www.w3.org/1999/02/22-rdf-syntax-ns#type> <http://www.w3.org/2004/03/trix/rdfg-1/Graph>
<http://xmlns.com/foaf/0.1/primaryTopic> <https://research.tib.eu/covid-19/entity/66lz6vfg>
<http://xmlns.com/foaf/0.1/topic> Anon_0
<http://www.ontologydesignpatterns.org/cp/owl/informationrealization.owl#realizes> <https://research.tib.eu/covid-19/data/entity/66lz6vfg>
<http://purl.org/net/provenance/ns#createdBy>
Anon_1   (more)
expand all