Invention Grant
- Patent Title: Deep learning system
-
Application No.: US17058126Application Date: 2019-05-21
-
Publication No.: US11900256B2Publication Date: 2024-02-13
- Inventor: David Macdara Moloney , Jonathan David Byrne , Léonie Raideen Buckley , Xiaofan Xu , Dexmont Alejandro Peña Carillo , Luis M. Rodríguez Martín de la Sierra , Carlos Márquez Rodríguez-Peral , Mi Sun Park , Cormac M. Brick , Alessandro Palla
- Applicant: Movidius Ltd.
- Applicant Address: NL Schiphol-Rijk
- Assignee: Intel Corporation
- Current Assignee: Intel Corporation
- Current Assignee Address: US CA Santa Clara
- Agency: Akona IP PC
- International Application: PCT/US2019/033373 2019.05.21
- International Announcement: WO2019/226686A 2019.11.28
- Date entered country: 2020-11-23
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G06N3/082 ; G06N3/04 ; G06T7/70 ; G06N3/044 ; G06N20/00

Abstract:
A machine learning system is provided to enhance various aspects of machine learning models. In some aspects, a substantially photorealistic three-dimensional (3D) graphical model of an object is accessed and a set of training images of the 3D graphical mode are generated, the set of training images generated to add imperfections and degrade photorealistic quality of the training images. The set of training images are provided as training data to train an artificial neural network.
Public/Granted literature
- US20210201526A1 DEEP LEARNING SYSTEM Public/Granted day:2021-07-01
Information query