Methods and systems for advanced and augmented training of deep neural networks using synthetic data and innovative generative networks

US11341368B2 · kind B2 · utility

Assignee

• Intel Corporation · US

Inventors

• Anbang Yao · Beijing, CN
• Shandong Wang · Beijing, CN
• Wenhua Cheng · Shanghai, CN
• Dongqi Cai · Beijing, CN
• Libin Wang · Dongxing District, CN
• Lin Xu · Fremont, US
• Ping Hu · Beijing, CN
• Yiwen Guo · Beijing, CN
• Liu Yang · Beijing, CN
• Yuqing Hou · Beijing, CN
• Zhou Su · Beijing, CN
• Yurong Chen · Beijing, CN

Key dates

• Filing date: Apr 7, 2017
• Grant date: May 24, 2022
• Expiry date: Jun 24, 2037

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/098
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

Methods and systems for advanced and augmented training of deep neural networks (DNNs) using synthetic data and innovative generative networks. A method includes training a DNN using synthetic data, training a plurality of DNNs using context data, associating features of the DNNs trained using context data with features of the DNN trained with synthetic data, and generating an augmented DNN using the associated features.