Patent · US Active

Representation learning using multi-task deep neural networks

US10089576B2 · kind B2 · utility

23Cited by
4References
17Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 28, 2015
Grant dateOct 2, 2018
Priority date
Expiry dateNov 18, 2036

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/10
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system may comprise one or more processors and memory storing instructions that, when executed by one or more processors, configure one or more processors to perform a number of operations or tasks, such as receiving a query or a document, and mapping the query or the document into a lower dimensional representation by performing at least one operational layer that shares at least two disparate tasks.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.