Minhao Cheng

Title: Minhao Cheng: Innovator in Machine Learning

Introduction

Minhao Cheng is a prominent inventor based in Los Angeles, CA. He has made significant contributions to the field of machine learning, particularly in developing techniques for training robust models. His innovative approach addresses challenges posed by adversarial input data, enhancing the reliability of machine learning systems.

Latest Patents

Minhao Cheng holds a patent for "Training robust machine learning models." This patent outlines techniques for training machine learning models using modified training data. The process involves generating first modified training data by altering labels in the original training data through parameterized label smoothing. The machine learning model is then trained using this modified data, which includes updating model weights and generating optimization parameters for future training.

Career Highlights

Cheng is associated with International Business Machines Corporation (IBM), where he applies his expertise in machine learning. His work focuses on improving the robustness of machine learning models, which is crucial for their application in real-world scenarios. His innovative techniques have the potential to significantly enhance the performance of machine learning systems.

Collaborations

Minhao Cheng collaborates with notable colleagues such as Pin-yu Chen and Sijia Liu. Together, they work on advancing the field of machine learning and developing solutions that address current challenges in the industry.

Conclusion

Minhao Cheng is a key figure in the realm of machine learning innovation. His contributions, particularly in training robust models, are paving the way for more reliable and effective machine learning applications. His work continues to influence the future of technology in this rapidly evolving field.