Zheda Mai

Title: Zheda Mai: Innovator in Online Class-Incremental Continual Learning

Introduction

Zheda Mai is a notable inventor based in Toronto, Canada. He has made significant contributions to the field of machine learning, particularly in the area of online class-incremental continual learning. His innovative approach addresses the challenges of preserving knowledge while adapting to new data.

Latest Patents

Zheda Mai holds a patent for a method titled "Online class-incremental continual learning with adversarial Shapley value." This method focuses on scoring training data samples to maintain latent decision boundaries for previously observed classes. It promotes learning from new images in an online data stream. The process involves receiving new input batches, retrieving relevant data from memory, and updating memory to retain previously learned knowledge. Additionally, the method employs data valuation based on KNN-SV for strategic data selection.

Career Highlights

Throughout his career, Zheda Mai has worked with prominent organizations, including LG Electronics Inc. and the University of Toronto. His experience in these institutions has allowed him to refine his skills and contribute to groundbreaking research in machine learning.

Collaborations

Zheda Mai has collaborated with talented individuals such as Dongsub Shim and Jihwan Jeong. These partnerships have fostered a creative environment for innovation and development in their respective fields.

Conclusion

Zheda Mai's work in online class-incremental continual learning showcases his dedication to advancing machine learning technologies. His innovative methods and collaborations highlight his impact on the field.