This inventor holds 2 USPTO granted patents and 1 published patent application. Top assignees: Microsoft Technology Licensing, LLC, Other. Active years: 2016-2022.
Company Filing History:
1 out of 56,162 
1 out of 834,350 Years Active: 2016-2022
Title: Yushun Wang: Innovator in Neural Network Optimization
Introduction
Yushun Wang is a prominent inventor based in Beijing, China. He has made significant contributions to the field of neural networks, particularly in optimizing computational graphs. With a total of 2 patents, his work has the potential to enhance the efficiency of neural network computations.
Latest Patents
Yushun Wang's latest patents include innovative methods for optimizing computational graphs of neural networks. The first patent discloses a method to optimize a neural network computational graph, which is essential for performing calculations on a computational platform. This method involves selecting layers that can be fused based on optimization rules to reduce data exchange frequency between the computational platform and off-chip memory. By carrying out fusion for at least two adjacent layers, the execution efficiency of the neural network computational platform is significantly improved.
Another notable patent focuses on generating and managing electronic documentation. This implementation provides a user interface for creating electronic documents, allowing users to access external data and interact with it seamlessly. The context data of the current document is utilized to enhance user experience and document quality.
Career Highlights
Yushun Wang has worked with notable companies, including Microsoft Technology Licensing, LLC. His experience in these organizations has contributed to his expertise in the field of technology and innovation.
Collaborations
Some of Yushun Wang's coworkers include Michael Todd Gillam and Kuo Zhang. Their collaboration has likely fostered a creative environment that encourages innovation and the development of groundbreaking technologies.
Conclusion
Yushun Wang is a distinguished inventor whose work in optimizing neural network computational graphs and electronic documentation has made a significant impact in the field of technology. His contributions continue to pave the way for advancements in neural network efficiency and user interaction with electronic documents.