Matches in Nanopublications for { ?s ?p ?o <https://w3id.org/kpxl/ios/ds/np/RAk_snGYBfeVwDRO-yDB_11HEW79Crp6AsKv0mpw1pYnA/assertion>. }
Showing items 1 to 19 of
19
with 100 items per page.
- DS-170007 type PositionPaper assertion.
- author-list _1 0000-0003-2415-8438 assertion.
- author-list__1 _2 0000-0002-0189-5817 assertion.
- author-list__2 _3 0000-0001-9079-039X assertion.
- DS-170007 isPartOf 2451-8492 assertion.
- 2451-8492 title "Data Science" assertion.
- DS-170007 title "The knowledge graph as the default data model for learning on heterogeneous knowledge" assertion.
- 0000-0001-9079-039X name "Victor de Boer" assertion.
- 0000-0003-2415-8438 name "Xander Wilcke" assertion.
- 0000-0002-0189-5817 name "Peter Bloem" assertion.
- 008xxew50 name "Faculty of Sciences, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands. Faculty of Spatial Economics, Vrije Universiteit Amsterdam, Amsterdam, The Netherlands" assertion.
- DS-170007 date "2017-10-17" assertion.
- DS-170007 abstract "In modern machine learning, raw data is the preferred input for our models. Where a decade ago data scientists were still engineering features, manually picking out the details we thought salient, they now prefer the data in their raw form. As long as we can assume that all relevant and irrelevant information is present in the input data, we can design deep models that build up intermediate representations to sift out relevant features. However, these models are often domain specific and tailored to the task at hand, and therefore unsuited for learning on heterogeneous knowledge: information of different types and from different domains. If we can develop methods that operate on this form of knowledge, we can dispense with a great deal more ad-hoc feature engineering and train deep models end-to-end in many more domains. To accomplish this, we first need a data model capable of expressing heterogeneous knowledge naturally in various domains, in as usable a form as possible, and satisfying as many use cases as possible. In this position paper, we argue that the knowledge graph is a suitable candidate for this data model. We further describe current research and discuss some of the promises and challenges of this approach." assertion.
- 0000-0003-2415-8438 email "w.x.wilcke@vu.nl" assertion.
- 0000-0001-9079-039X affiliation 008xxew50 assertion.
- 0000-0003-2415-8438 affiliation 008xxew50 assertion.
- 0000-0002-0189-5817 affiliation 008xxew50 assertion.
- DS-170007 issue "1-2" assertion.
- DS-170007 volume "1" assertion.