This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Yonsei 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: Jong Youn Noh: Inventor in Machine Learning
Introduction
Jong Youn Noh is an inventor based in Seoul, South Korea, and is associated with Yonsei University. His patent work addresses confidence calibration in image classification, with a focus on adaptive label smoothing.
Latest Patents
Noh is named on one patent: “Apparatus and Method for Confidence Calibration Based on Adaptive Label Smoothing.” The invention describes a computing device that inputs image data into an image classification model and obtains logits and prediction probabilities. The model then produces a label-smoothing loss function using learnable margin parameters, label-smoothing weights based on classification difficulty, or both.
Career Highlights
Noh’s patent reflects research into improving confidence calibration for image classification models. The disclosed approach adapts label smoothing to account for the difficulty of classifying an image.
Collaborations
Noh’s listed coworkers include Bum Sub Ham and Hye Kang Park. His association with Yonsei University provides the institutional context for his patent work.
Conclusion
Jong Youn Noh’s patent focuses on adaptive label smoothing as a method for calibrating confidence in image classification, highlighting his contribution to machine-learning innovation.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile