Cupertino, CA, United States of America

Brandon Bolong Lee

USPTO Granted Patents = 1 

Average Co-Inventor Count = 4.0

ph-index = 1


Company Filing History:


Years Active: 2025

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Innovations of Brandon Bolong Lee

Introduction

Brandon Bolong Lee is an accomplished inventor based in Cupertino, CA. He has made significant contributions to the field of machine learning, particularly in the area of mitigating temporal generalization losses in models. His innovative approach aims to enhance the stability and performance of machine learning systems over time.

Latest Patents

Brandon holds a patent titled "Mitigating temporal generalization for a machine learning model." This patent discloses methods for identifying, removing, modifying, and transforming features that may have an unstable relationship with target outcomes over time. The implementation of a more stable representation can be initiated through this process. Temporal stability measures (TSMs) for model features can be determined based on variable performance metrics (VPMs). The patent also outlines how model feature modifications can be recommended based on TSMs, which may include pruning, transforming, or adding features. Additionally, temporal stability information can be presented through a user-friendly dashboard interface.

Career Highlights

Brandon is currently employed at AT&T Intellectual Property I, L.P., where he continues to develop innovative solutions in the realm of technology and machine learning. His work is characterized by a commitment to improving the reliability and effectiveness of machine learning models.

Collaborations

Brandon collaborates with talented individuals such as Andrew Campbell and Ana Armenta, contributing to a dynamic and innovative work environment.

Conclusion

Brandon Bolong Lee's contributions to machine learning through his patent and work at AT&T highlight his role as a forward-thinking inventor. His efforts to mitigate temporal generalization losses are paving the way for more stable and effective machine learning applications.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…