Yu Gong

Title: Yu Gong - Innovator in Neural Network Calculation Methods

Introduction

Yu Gong is a prominent inventor based in Jiangsu, China. He has made significant contributions to the field of analog integrated circuits, particularly in the development of methods and circuits that enhance neural network calculations. His innovative approach focuses on achieving high-speed and low-power consumption solutions.

Latest Patents

Yu Gong holds a patent for a "Multiply-accumulate calculation method and circuit suitable for neural network." This invention addresses the challenges of large-scale multiply-accumulate calculations in neural networks. The circuit comprises a multiplication calculation circuit array and an accumulation calculation circuit, designed to optimize performance while minimizing power usage. The multiplication calculation circuit array consists of multiple groups of circuits, which utilize real-time quantization for improved efficiency. The accumulation calculation circuit features a series of components that dynamically control iterations and data accumulation, catering to the varying calculation scales of different network layers.

Career Highlights

Yu Gong is affiliated with Southeast University, where he continues to advance research in integrated circuits and neural networks. His work has garnered attention for its practical applications in modern computing and artificial intelligence.

Collaborations

Yu Gong collaborates with notable colleagues, including Bo Liu and Wei Ge, who contribute to his research endeavors and innovations in the field.

Conclusion

Yu Gong's contributions to neural network calculation methods exemplify the intersection of innovation and technology. His work not only enhances computational efficiency but also paves the way for future advancements in artificial intelligence.