Di Xie

Title: Di Xie - Innovator in Deep Neural Network Technologies

Introduction

Di Xie is a prominent inventor based in Zhejiang, China. He has made significant contributions to the field of deep learning and neural networks. With a total of six patents to his name, Xie's work focuses on improving the efficiency and effectiveness of deep neural network operations.

Latest Patents

One of Di Xie's latest patents is an operation method and apparatus for a network layer in a deep neural network. This invention involves acquiring a weighted tensor of the network layer, which includes multiple filters. The method converts each filter into a linear combination of fixed-point convolution kernels, allowing for efficient convolution operations on input data. The result is a weighted sum that determines the output data of the network layer.

Another notable patent is related to a deep neural network training method and apparatus. This method includes obtaining task attributes of nodes in a tree-like network topology and performing cluster analysis based on these attributes. By training network parameters of parent nodes, the overall training of the deep neural network is optimized, enhancing operation efficiency.

Career Highlights

Di Xie is currently employed at Hangzhou Hikvision Digital Technology Co., Ltd. His role involves developing innovative solutions that leverage deep learning technologies. His expertise in neural networks has positioned him as a key player in advancing the capabilities of artificial intelligence.

Collaborations

Di Xie collaborates with talented individuals such as Shiliang Pu and Lulu Zhou. Together, they work on various projects that aim to push the boundaries of deep learning and its applications.

Conclusion

Di Xie's contributions to deep neural networks and his innovative patents highlight his role as a leading inventor in the field. His work continues to influence advancements in artificial intelligence and machine learning technologies.