Patent · US Active

Domain adaptation of deep neural networks

US11580405B2 · kind B2 · utility

1Cited by

5References

20Claims

0Family size

Assignee

SAP SE · DE

Inventors

Erick David Santillán Perez · Leimen, DE
David Kernert · Heidelberg, DE

Key dates

Filing date	Dec 26, 2019
Grant date	Feb 14, 2023
Priority date	—
Expiry date	May 10, 2041

Classification

Technology area (CPC G)Physics
CPC primaryG06V10/82
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Disclosed herein are system, method, and computer program product embodiments for adapting machine learning models for use in additional applications. For example, feature extraction models are readily available for use in applications such as image detection. These feature extraction models can be used to label inputs (such as images) in conjunction with other deep neural network models. However, in adapting the feature extraction models to these uses, it becomes problematic to improve the quality of their results on target data sets, as these feature extraction models are large and resistant to retraining. Approaches disclosed herein include a transfer layer for providing fast retraining of machine learning models.

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