Menlo Park, CA, United States of America

Peng Qi

USPTO Granted Patents = 9 

Average Co-Inventor Count = 3.2

ph-index = 1


Company Filing History:


Years Active: 2023-2025

Loading Chart...
9 patents (USPTO):Explore Patents

Title: Innovations by Inventor Peng Qi

Introduction

Peng Qi is a notable inventor based in Menlo Park, CA, who has made significant contributions to the field of machine learning and predictive modeling. With a total of 9 patents to his name, he has developed innovative solutions that enhance the capabilities of online systems.

Latest Patents

One of Peng Qi's latest patents is titled "Machine-learned neural network architectures for incremental lift predictions using embeddings." This invention involves an online system that trains a machine-learned lift prediction model configured as a neural network. The model is designed to determine lift predictions for users and items associated with the online system. By utilizing a neural network, the model can flexibly process information from various formats, improving upon existing methods. The model includes two portions: one for generating control predictions and another for treatment predictions, sharing a subset of parameters to capture essential information.

Another significant patent focuses on "Incrementally updating embeddings for use in a machine learning model by accounting for effects of the updated embeddings on the machine learning model." This invention is utilized in an online concierge system that predicts user interactions with items based on user and item embeddings. The system generates updated embeddings that reflect recent user interactions without the need for retraining the model. It compares the performance of the model using updated embeddings against existing ones and adjusts them accordingly to maintain optimal performance.

Career Highlights

Peng Qi is currently employed at Maplebear Inc., where he continues to innovate and develop advanced machine learning technologies. His work has positioned him as a key figure in the field, contributing to the evolution of predictive modeling techniques.

Collaborations

Throughout his career, Peng has collaborated with talented individuals such as Changyao Chen and Weian Sheng, further enhancing the impact of his inventions.

Conclusion

Peng Qi's contributions to machine learning and predictive modeling demonstrate his innovative spirit and commitment to advancing technology. His patents reflect a deep understanding of complex systems and a drive to improve user experiences in online environments.

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