Yi Shan

Title: Yi Shan: Innovator in High Parallelism Computing and Neural Network Compression

Introduction

Yi Shan is a prominent inventor based in Beijing, China. He has made significant contributions to the fields of computing systems and artificial neural networks. With a total of 12 patents to his name, his work focuses on enhancing computational efficiency and resource utilization.

Latest Patents

Yi Shan's latest patents include a "High Parallelism Computing System and Instruction Scheduling Method Thereof." This invention discloses a computing system that comprises an instruction reading and distribution module, an internal buffer, and multiple function modules. The system is designed to read instructions in a specific order, distributing them to corresponding function modules while avoiding deadlocks caused by instruction dependencies through topological sorting of a directed acyclic graph.

Another notable patent is the "Compression Method for Deep Neural Networks with Load Balance." This invention addresses the challenge of compressing dense neural networks into sparse ones efficiently. It aims to improve the utilization of hardware resources by considering load balance during the compression process.

Career Highlights

Throughout his career, Yi Shan has worked with notable companies such as Xilinx, Inc. and Xilinx Technology Beijing Limited. His experience in these organizations has allowed him to develop innovative solutions that push the boundaries of technology.

Collaborations

Yi Shan has collaborated with talented individuals in his field, including Song Han and Lingzhi Sui. These partnerships have contributed to the advancement of his research and inventions.

Conclusion

Yi Shan is a distinguished inventor whose work in high parallelism computing and neural network compression has made a significant impact on technology. His innovative patents reflect his commitment to enhancing computational efficiency and resource utilization.