Xiaoyi Zhang

Title: Innovations by Xiaoyi Zhang

Introduction

Xiaoyi Zhang is a notable inventor based in Sunnyvale, CA. He has made significant contributions to the field of technology, particularly in machine learning and gesture recognition. With a total of 2 patents, his work reflects a commitment to advancing innovative solutions.

Latest Patents

Xiaoyi Zhang's latest patents include "Two-stage training with non-randomized and randomized data." This invention addresses position bias and other types of bias in machine-learned models by employing a two-phase training approach. The first phase utilizes non-randomized training data, which is essential for deep learning models that require substantial amounts of data. The second phase revises the model using randomized training data to eliminate bias, ensuring the model operates in an unbiased manner without needing additional randomized data.

Another significant patent is the "Automated E-tran application." This invention involves techniques for text entry using gestures, where a camera captures a frame to detect the user's face. By aligning landmarks to the face, the system can extract images of the left and right eyes, resize them, and compare them to a calibration template. This allows for the determination of eye gaze direction, which can predict characters or words for text-based messages.

Career Highlights

Xiaoyi Zhang is currently employed at Microsoft Technology Licensing, LLC, where he continues to innovate and develop new technologies. His work at Microsoft has allowed him to collaborate with other talented individuals in the field.

Collaborations

Some of his notable coworkers include Daniel Sairom Krishnan Hewlett and Dan Liu, who contribute to the collaborative environment that fosters innovation.

Conclusion

Xiaoyi Zhang's contributions to technology through his patents demonstrate his expertise and dedication to innovation. His work in machine learning and gesture recognition continues to pave the way for future advancements in these fields.