This inventor holds 1 USPTO granted patent. Top assignees: Zhejiang Lab, Zhejiang University. Active years: 2026.
Company Filing History:
1 out of 182 
1 out of 1,270 
Years Active: 2026
Title: Junhai Fan: Innovator in Neural Network Acceleration
Introduction
Junhai Fan is a prominent inventor based in Zhejiang, China. He has made significant contributions to the field of neural network acceleration, particularly through his innovative patent. His work focuses on enhancing the efficiency of convolution computations, which are crucial for various applications in artificial intelligence.
Latest Patents
Junhai Fan holds a patent titled "Parallel method and device for convolution computation and data loading of neural network accelerator." This patent discloses a method that requires two input feature maps and two convolution kernel cache blocks. The method sequentially stores the input feature maps and 64 convolution kernels into cache sub-blocks according to a loading length. This approach allows for the execution of convolution computation while simultaneously loading data for the next group of 64 convolution kernels. He has 1 patent to his name.
Career Highlights
Throughout his career, Junhai Fan has worked with notable institutions such as Zhejiang Lab and Zhejiang University. His experience in these organizations has allowed him to develop and refine his innovative ideas in the realm of neural networks.
Collaborations
Junhai Fan has collaborated with esteemed colleagues, including Guoquan Zhu and De Ma. These partnerships have contributed to the advancement of his research and the successful development of his patent.
Conclusion
Junhai Fan is a key figure in the field of neural network acceleration, with a focus on improving convolution computation methods. His innovative patent and collaborations highlight his commitment to advancing technology in this area.