This inventor holds 3 USPTO granted patents and 3 published patent applications. Top assignees: Northeastern University, College of William and Mary. Active years: 2026.
Company Filing History:
3 out of 685 
1 out of 45 
Years Active: 2026
Title: Yanzhi Wang: Innovator in Deep Neural Network Compression
Introduction
Yanzhi Wang is a prominent inventor based in Newton, MA (US). He has made significant contributions to the field of deep learning, particularly in the optimization of deep neural networks (DNN) for mobile devices. His innovative approach focuses on enhancing the efficiency of DNN models, making them more suitable for real-time applications.
Latest Patents
Yanzhi Wang holds a patent for "Computer-implemented methods and systems for DNN weight pruning for real-time execution on mobile devices." This patent describes a method for compressing a DNN model through weight pruning, which accelerates DNN inference on mobile devices. The process involves intra-convolution kernel pruning to create sparse convolution patterns and inter-convolution kernel pruning to achieve connectivity sparsity. The final step includes training the compressed DNN model to ensure optimal performance.
Career Highlights
Yanzhi Wang is affiliated with Northeastern University, where he continues to advance research in deep learning and artificial intelligence. His work has garnered attention for its practical applications in mobile technology, contributing to the growing field of machine learning.
Collaborations
Yanzhi Wang collaborates with Xiaolong Ma, a fellow researcher, to further explore innovations in DNN optimization and mobile applications.
Conclusion
Yanzhi Wang's contributions to deep neural network compression represent a significant advancement in the field of artificial intelligence. His innovative methods are paving the way for more efficient mobile applications, showcasing the potential of DNN technology in everyday devices.