Zheren Dai

Title: Zheren Dai: Innovator in Spiking Neural Network Acceleration

Introduction

Zheren Dai is a prominent inventor based in Hangzhou, China. He has made significant contributions to the field of neural networks, particularly in the development of innovative acceleration methods for spiking neural networks. His work focuses on enhancing computational efficiency and addressing challenges associated with spiking neural network models.

Latest Patents

Zheren Dai holds a patent titled "Event-driven accelerator supporting inhibitory spiking neural network." This patent describes a spiking neural network acceleration method that constructs an approximate computation model based on a spiking neuron model and a spiking coding mode. The model leverages the characteristic that spiking frequency domain coding ignores the time semantics of a spiking sequence. It compresses the distribution of spiking signals over time, significantly reducing the spiking routing process and subsequent neural computation. The time-driven accelerator reorganizes the computation process of the spiking neural network, implementing a deduplication queue and a bitmap to address spiking jitter, thereby providing efficient support for inhibitory spiking neural networks.

Career Highlights

Zheren Dai is affiliated with the Electric Power Research Institute of State Grid Zhejiang Electric Power Co., Ltd. His role at this institution allows him to apply his innovative ideas in practical settings, contributing to advancements in electrical power research and technology.

Collaborations

Zheren Dai collaborates with notable colleagues, including Rui Han and Donglian Qi. Their teamwork fosters a creative environment that enhances the development of cutting-edge technologies in their field.

Conclusion

Zheren Dai's contributions to spiking neural networks exemplify the impact of innovative thinking in technology. His patent and collaborative efforts highlight the importance of research and development in advancing neural network applications.