Cambridge, United Kingdom

Kwun Ho Ngan


 

Average Co-Inventor Count = 3.0

ph-index = 1


Company Filing History:


Years Active: 2025

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

Title: The Innovative Mind of Kwun Ho Ngan

Introduction

Kwun Ho Ngan is a notable inventor based in Cambridge, GB. He has made significant contributions to the field of computer science, particularly in the area of convolutional neural networks. His innovative work has led to the development of a unique patent that enhances image feature identification.

Latest Patents

Kwun Ho Ngan holds a patent for a computer-implemented method titled "Kernel transfer." This method involves obtaining outputs from multiple kernels in an extraction layer of a trained convolutional neural network. The process includes aggregating outputs to generate an aggregate map, resizing these maps, clustering region maps, and training a second convolutional neural network using input samples from a different domain. This innovative approach aims to improve the efficiency and accuracy of image processing.

Career Highlights

Kwun Ho Ngan is currently employed at Fujitsu Corporation, where he continues to push the boundaries of technology. His work at Fujitsu has allowed him to collaborate with other talented professionals in the field, contributing to advancements in artificial intelligence and machine learning.

Collaborations

Some of his notable coworkers include Artur Garcez and Joseph Townsend. Their combined expertise fosters a collaborative environment that drives innovation and research within the company.

Conclusion

Kwun Ho Ngan's contributions to the field of computer science, particularly through his patent on kernel transfer, showcase his innovative spirit and dedication to advancing technology. His work at Fujitsu Corporation and collaborations with esteemed colleagues further highlight his impact on the industry.

This text is generated by artificial intelligence and may not be accurate.
Please report any incorrect information to support@idiyas.com
Loading…