Back to Search
Start Over
Data mining with tensor decompositions
- Source :
- HAL, GRETSI 2019, GRETSI 2019-XXVIIème Colloque francophone de traitement du signal et des images, GRETSI 2019-XXVIIème Colloque francophone de traitement du signal et des images, Aug 2019, Lille, France
- Publication Year :
- 2019
- Publisher :
- HAL CCSD, 2019.
-
Abstract
- National audience; ext mining is addressed by identifying multiview models. Following the recent works of A.Anandkumar, we show that the algorithms previously proposed exhibit important drawbacks. The algorithm subsequently proposed permits to decompose a nonnegative tensor built with sample joint probabilities. It compares favorably to the former on synthetically generated data sets.
Details
- Language :
- English
- Database :
- OpenAIRE
- Journal :
- HAL, GRETSI 2019, GRETSI 2019-XXVIIème Colloque francophone de traitement du signal et des images, GRETSI 2019-XXVIIème Colloque francophone de traitement du signal et des images, Aug 2019, Lille, France
- Accession number :
- edsair.dedup.wf.001..4a6d81d6a081c51bd3efc7b155b69478