Wenhua Cheng

Title: Innovations of Wenhua Cheng

Introduction

Wenhua Cheng is a prominent inventor based in Beijing, China. He has made significant contributions to the field of deep learning and neural networks. With a total of 10 patents, his work has advanced the capabilities of artificial intelligence technologies.

Latest Patents

One of his latest patents focuses on methods and systems for budgeted and simplified training of deep neural networks (DNNs). This innovation involves training a DNN using a variety of training sub-images derived from down-sampled training images. Additionally, it includes testing the trained DNN with testing sub-images from down-sampled testing images. Another aspect of his patent describes a recurrent deep Q-network (RDQN) that incorporates a local attention mechanism between a convolutional neural network (CNN) and a long-short time memory (LSTM). In this system, feature maps are generated by the CNN from input images, and both hard and soft attention mechanisms are applied to enhance the selection and weighting of these feature maps. The resulting weighted feature maps are stored in the LSTM, allowing for the calculation of Q values for different actions based on the stored data.

Career Highlights

Wenhua Cheng is currently employed at Intel Corporation, where he continues to innovate and develop cutting-edge technologies. His work at Intel has positioned him as a key player in the advancement of artificial intelligence and machine learning.

Collaborations

Wenhua collaborates with talented individuals such as Shandong Wang and Yiwen Guo, contributing to a dynamic and innovative work environment.

Conclusion

Wenhua Cheng's contributions to the field of deep learning and neural networks are noteworthy. His innovative patents and work at Intel Corporation highlight his role as a leading inventor in the technology sector.