Mingge Deng

Title: Innovations of Mingge Deng

Introduction

Mingge Deng is a notable inventor based in Mountain View, CA. He has made significant contributions to the field of technology, particularly in the areas of anomaly detection and matrix factorization. With a total of 6 patents to his name, Deng continues to push the boundaries of innovation.

Latest Patents

One of his latest patents is titled "Anomaly detection with local outlier factor." This method involves receiving an anomaly detection query from a user, which requests data processing hardware to identify anomalies in a dataset. The process includes training a model using the dataset and employing a local outlier factor (LOF) algorithm to determine local deviation scores for each example in the dataset. If the scores meet a specified threshold, the respective examples are classified as anomalous and reported to the user.

Another significant patent is "Scalable matrix factorization in a database." This invention encompasses methods, systems, and apparatus for scalable matrix factorization. The method begins with obtaining a Structured Query Language (SQL) query to create a matrix factorization model based on training data. It generates SQL sub-queries that exclude non-scalable functions and ultimately produces a matrix factorization model based on the training data and the scalable SQL sub-queries.

Career Highlights

Mingge Deng is currently employed at Google Inc., where he applies his expertise in data processing and machine learning. His work has been instrumental in developing innovative solutions that enhance data analysis and processing capabilities.

Collaborations

Deng collaborates with talented individuals such as Amir H Hormati and Zichuan Ye, contributing to a dynamic work environment that fosters creativity and innovation.

Conclusion

Mingge Deng's contributions to technology through his patents and work at Google Inc. highlight his role as a leading inventor in the field. His innovative approaches to anomaly detection and matrix factorization continue to influence advancements in data processing.