Invention Grant
- Patent Title: Systems and methods of generating datasets for training neural networks
-
Application No.: US16682880Application Date: 2019-11-13
-
Publication No.: US11227378B2Publication Date: 2022-01-18
- Inventor: Rainer Burkhardt , Anil Kumar Vuppala , Tridivesh Jena
- Applicant: Software AG
- Applicant Address: DE Darmstadt
- Assignee: Software AG
- Current Assignee: Software AG
- Current Assignee Address: DE Darmstadt
- Agency: Nixon & Vanderhye P.C.
- Main IPC: B23K31/12
- IPC: B23K31/12 ; G06N3/08 ; B23K26/24 ; G06T7/00 ; G06N20/00
Abstract:
A system for generating training datasets is provided. The system uses base images to generate a large number of images that include non-defective and defective characteristics. The generated images are then used to train a model that may be used to predict defects in real world images of a manufacturing process.
Public/Granted literature
- US20210142467A1 SYSTEMS AND METHODS OF GENERATING DATASETS FOR TRAINING NEURAL NETWORKS Public/Granted day:2021-05-13
Information query
IPC分类:
