Company Filing History:
Years Active: 2020-2024
Title: Hsiang-Tsun Li: Innovator in Dynamic Fixed-Point Quantization
Introduction
Hsiang-Tsun Li is a prominent inventor based in Taichung, Taiwan. He has made significant contributions to the field of convolutional neural networks (CNNs) through his innovative patents. With a total of 3 patents, Li's work focuses on enhancing the efficiency and performance of neural networks.
Latest Patents
One of his latest patents is titled "Low precision and coarse-to-fine dynamic fixed-point quantization design in convolution neural network." This invention involves inputting data into a floating pre-trained CNN to generate floating feature maps for each layer. A statistical analysis is performed on these feature maps to create a dynamic quantization range for each layer. The proposed methodologies then quantize the CNN model, enabling low-precision fixed-point arithmetic operations for generating a fixed-point inferred CNN model.
Another notable patent is "Deep neural network with low-precision dynamic fixed-point in reconfigurable hardware design." This system operates a floating-to-fixed arithmetic framework on hardware such as a central processing unit (CPU). It allows for the computation of a floating pre-trained CNN model into a dynamic fixed-point CNN model, which can be implemented on resource-limited embedded systems like mobile phones or video cameras.
Career Highlights
Hsiang-Tsun Li is currently employed at Kneron Co., Ltd., where he continues to push the boundaries of technology in the field of artificial intelligence. His work is instrumental in developing efficient algorithms that can be utilized in various applications.
Collaborations
Li collaborates with talented individuals such as Bike Xie and Junjie Su, contributing to a dynamic team focused on advancing neural network technologies.
Conclusion
Hsiang-Tsun Li's innovative patents and contributions to the field of convolutional neural networks highlight his role as a leading inventor in the technology sector. His work not only enhances the performance of neural networks but also paves the way for future advancements in artificial intelligence.