Yanan Sun

Title: Yanan Sun: Innovator in Neural Network Technologies

Introduction

Yanan Sun is a prominent inventor based in Chengdu, China. He has made significant contributions to the field of neural networks and architecture search, holding three patents that showcase his innovative approaches.

Latest Patents

One of his latest patents is titled "Method for differentiable architecture search based on a hierarchical grouping mechanism." This method involves obtaining a target dataset and selecting a specific number of normal and reduction cells. The reduction cells are strategically placed within the architecture, and the initial search network is trained to optimize a cost function. This process allows for either a one-level or two-level search, ultimately leading to the construction of a target network.

Another notable patent is the "Face recognition method based on evolutionary convolutional neural network." This method enhances the design of convolutional neural networks by utilizing a genetic algorithm for optimizing architecture and connection weights. It reduces reliance on artificial experience and improves the diversity of neural network structures through a variable-length genetic encoding algorithm.

Career Highlights

Yanan Sun is affiliated with Sichuan University, where he continues to advance research in neural networks and machine learning. His work has garnered attention for its innovative methodologies and practical applications in technology.

Collaborations

He collaborates with notable colleagues, including Jiancheng Lv and Zhenan He, contributing to a dynamic research environment that fosters innovation.

Conclusion

Yanan Sun's contributions to neural network technologies and architecture search exemplify the spirit of innovation in the field. His patents reflect a commitment to advancing technology and improving methodologies in machine learning.