Patent · US Active

Complex-valued neural network with learnable non-linearities in medical imaging

US11580381B2 · kind B2 · utility

2Cited by

0References

20Claims

0Family size

Assignee

Siemens Healthcare Limited · DE

Inventors

Guillaume Daval Frerot · Lawrenceville, US
Xiao Chen · Somerville, US
Simon Arberet · Princeton, US
Boris Mailhe · Plainsboro, US
Mariappan S. Nadar · Plainsboro, US
Peter Speier · Erlangen, DE
Mathias Nittka · Baiersdorf, DE

Key dates

Filing date	Apr 25, 2019
Grant date	Feb 14, 2023
Priority date	—
Expiry date	Dec 15, 2041

Classification

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

Abstract

For machine training and application of a trained complex-valued machine learning model, an activation function of the machine learning model, such as a neural network, includes a learnable parameter that is complex or defined in a complex domain with two dimensions, such as real and imaginary or magnitude and phase dimensions. The complex learnable parameter is trained for any of various applications, such as MR fingerprinting, other medical imaging, or non-medical uses.

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