Ruili Wu

Title: Ruili Wu: Innovator in Deep Neural Network Hardware Acceleration

Introduction

Ruili Wu is a prominent inventor based in Jiangsu, China. She has made significant contributions to the field of deep learning through her innovative patent. Her work focuses on enhancing the efficiency of hardware accelerators used in deep neural networks.

Latest Patents

Ruili Wu holds a patent for a "Deep Neural Network Hardware Accelerator Based on Power Exponential Quantization." This invention comprises several components, including an AXI-4 bus interface, input and output cache areas, a weighting cache area, and a configurable state controller module. The design utilizes a line cache structure for both input and output areas. The encoder in the system encodes weightings based on an ordered quantization set, which stores possible values of the absolute weightings after quantization. The accelerator performs shift calculations using data from the input and weighting index cache areas, significantly reducing the need for computing resources and increasing calculation efficiency.

Career Highlights

Ruili Wu is affiliated with Southeast University, where she continues to advance her research in hardware acceleration technologies. Her innovative approach has positioned her as a key figure in the development of efficient deep learning systems.

Collaborations

Ruili Wu collaborates with notable colleagues, including Shengli Lu and Wei Pang, who contribute to her research endeavors.

Conclusion

Ruili Wu's contributions to deep neural network hardware acceleration exemplify her innovative spirit and dedication to advancing technology. Her patent reflects a significant step forward in improving computational efficiency in deep learning applications.