Hsinchu, Taiwan

Tyng-Luh Liu

This inventor holds 1 USPTO granted patent. Top assignee: National Tsing Hua University. Active years: 2022.


% Patents Active = 100.0

Average Co-Inventor Count = 3.0

ph-index = 1


Company Filing History:


Years Active: 2022

Loading Chart...
1 patent (USPTO):Explore Patents

Title: Tyng-Luh Liu: Innovator in Artificial Neural Networks

Introduction

Tyng-Luh Liu is a prominent inventor based in Hsinchu, Taiwan. He has made significant contributions to the field of artificial intelligence, particularly in the development of electronic apparatuses and methods for compressing artificial neural networks. His innovative work is paving the way for advancements in machine learning technologies.

Latest Patents

Tyng-Luh Liu holds a patent for an "Electronic apparatus and compression method for artificial neural network." This invention provides a compression method specifically designed for artificial neural networks that contain multiple convolution layers. The method involves setting a first pruning layer to couple with the Lth convolution layer, tuning weighting values, and generating a compressed version of the convolution layer by removing redundancy channels. This innovative approach enhances the efficiency of artificial neural networks.

Career Highlights

Tyng-Luh Liu is affiliated with National Tsing Hua University, where he continues to engage in cutting-edge research and development. His work focuses on improving the performance and efficiency of artificial intelligence systems, contributing to the academic and technological landscape in Taiwan.

Collaborations

Tyng-Luh Liu has collaborated with notable colleagues, including Hwann-Tzong Chen and Chih-Yao Chiu. These partnerships have fostered a collaborative environment that encourages innovation and the sharing of ideas in the field of artificial intelligence.

Conclusion

Tyng-Luh Liu's contributions to artificial neural networks exemplify the spirit of innovation in technology. His work not only advances the field of artificial intelligence but also inspires future research and development in this critical area.

Profile summary based on public USPTO records.
Please report any incorrect information to [email protected]
Loading…