Ge Yang

Title: Ge Yang: Innovator in Neural Network Technologies

Introduction

Ge Yang is a prominent inventor based in Bellevue, WA (US), known for his contributions to the field of neural networks. With a total of 4 patents to his name, he has made significant strides in optimizing machine learning processes.

Latest Patents

One of Ge Yang's latest patents is titled "Hyperparameter transfer via the theory of infinite-width neural networks." This invention provides systems and methods for tuning hyperparameters associated with small neural network models and transferring them to larger models. By parameterizing the large neural network in accordance with a specific scheme, the invention allows for significant savings in computation cycles and energy. Another notable patent is "Selecting a neural network architecture for a supervised machine learning problem." This patent outlines methods for selecting the most suitable neural network for a given machine learning problem by computing expressivity and trainability measures for multiple untrained candidate networks.

Career Highlights

Ge Yang is currently employed at Microsoft Technology Licensing, LLC, where he continues to innovate in the realm of machine learning and neural networks. His work focuses on enhancing the efficiency and effectiveness of neural network applications.

Collaborations

Ge has collaborated with notable colleagues such as Nicolo Fusi and Saeed Amizadeh, contributing to a dynamic and innovative work environment.

Conclusion

Ge Yang's contributions to neural network technologies exemplify the impact of innovative thinking in the field of machine learning. His patents not only advance the technology but also pave the way for more efficient computational methods.