Xiaolong Ma

Title: Innovations of Xiaolong Ma in Deep Neural Network Compression

Introduction

Xiaolong Ma is an accomplished inventor based in Boston, MA (US). He has made significant contributions to the field of deep learning, particularly in the area of optimizing deep neural networks for mobile devices. His work focuses on enhancing the efficiency of neural network models, making them more suitable for real-time applications.

Latest Patents

Xiaolong Ma holds a patent titled "Computer-implemented methods and systems for DNN weight pruning for real-time execution on mobile devices." This innovative method involves compressing a deep neural network (DNN) model through weight pruning. The process accelerates DNN inference on mobile devices by performing intra-convolution kernel pruning and inter-convolution kernel pruning. These steps generate sparse convolution patterns and connectivity sparsity, respectively, ultimately leading to a more efficient DNN model.

Career Highlights

Xiaolong Ma is affiliated with Northeastern University, where he contributes to research and development in the field of artificial intelligence. His expertise in deep learning and neural network optimization has positioned him as a key figure in advancing mobile computing technologies.

Collaborations

Xiaolong Ma collaborates with Yanzhi Wang, who is also involved in research related to deep learning and neural networks. Their partnership enhances the scope and impact of their work in the field.

Conclusion

Xiaolong Ma's innovative approaches to deep neural network compression are paving the way for more efficient mobile applications. His contributions are vital in the ongoing evolution of artificial intelligence technologies.