This inventor holds 1 USPTO granted patent. Top assignee: Sungkyunkwan University. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Innovations by Dong Eon Jeong
Dong Eon Jeong is a notable inventor based in Suwon, South Korea. He has made significant contributions to the field of neural networks, particularly in the area of model training methods and apparatus. His work is characterized by a focus on enhancing the efficiency and effectiveness of neural network training processes.
Latest Patents
Dong Eon Jeong holds 1 patent for a neural network model training method and apparatus. This innovative method includes a first training operation that trains the neural network model with original data. The first training operation generates a first feature map and a first class activation map for the original data. Additionally, a second training operation is conducted using adversarial data transformed from the original data. This operation generates a second feature map and a second class activation map, ensuring that the second class activation map aligns with the first through logit pairing.
Career Highlights
Dong Eon Jeong is affiliated with Sungkyunkwan University, where he contributes to research and development in artificial intelligence and machine learning. His academic background and research focus have positioned him as a key figure in advancing neural network technologies.
Collaborations
He collaborates with Jin Sub Lee, working together on various projects that aim to push the boundaries of neural network applications. Their partnership exemplifies the importance of teamwork in driving innovation in technology.
Conclusion
Dong Eon Jeong's contributions to neural network model training methods highlight his role as an influential inventor in the field. His innovative approaches continue to shape the future of artificial intelligence and machine learning.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
