Company Filing History:
Years Active: 2025
Title: Innovations by Dongkuan Xu
Introduction
Dongkuan Xu is a prominent inventor based in Los Altos, California. He has made significant contributions to the field of neural networks, with a focus on improving their efficiency and performance. With two patents to his name, Xu is recognized for his innovative approaches to neural network pruning and activation feature maps.
Latest Patents
Xu's latest patents include a "Neural network pruning method and system via layerwise analysis." This invention allows for the pruning of neural networks by utilizing the inputs and outputs generated by a reference neural network. The result is a pruned neural network that retains a subset of the weights from the original reference network. Another notable patent is for "Bank-balanced-sparse activation feature maps for neural network models." This invention describes methods to generate bank-balanced-sparse activation neural network models. It involves a neural network sparsification engine that determines a deep neural network model with multiple hidden layers, optimizing the bank size, layout, and target sparsity for improved performance.
Career Highlights
Dongkuan Xu is currently employed at Moffett International Co., Limited, where he continues to develop innovative solutions in the field of artificial intelligence and machine learning. His work has garnered attention for its practical applications in various industries.
Collaborations
Xu collaborates with talented individuals such as Enxu Yan and Jiachao Liu, contributing to a dynamic team focused on advancing neural network technologies.
Conclusion
Dongkuan Xu's contributions to neural network technology through his patents demonstrate his commitment to innovation in the field. His work continues to influence advancements in artificial intelligence and machine learning.