Bokaro Steel, India

Guarav Kumar


Average Co-Inventor Count = 1.0


Company Filing History:


Years Active: 2025

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

Title: Guarav Kumar: Innovator in Deep Neural Network Compression

Introduction

Guarav Kumar is a notable inventor based in Bokaro Steel, India. He has made significant contributions to the field of artificial intelligence, particularly in the area of deep neural networks. His innovative approach to compressing neural networks has garnered attention in the tech community.

Latest Patents

Guarav Kumar holds a patent for a method titled "Deep neural network compression based on filter importance." This patent outlines techniques for compressing deep neural networks using a structured filter pruning method that is both extensible and effective. The method involves determining importance scores for filters of layers in a neural network model that has been previously trained for an inferencing task. Filters that do not meet a specified threshold importance score are removed, resulting in a compressed neural network model.

Career Highlights

Guarav Kumar is currently employed at GE Precision Healthcare LLC, where he applies his expertise in neural networks to advance healthcare technologies. His work focuses on improving the efficiency and performance of deep learning models, which are crucial in various applications within the healthcare sector.

Collaborations

Guarav has collaborated with talented individuals such as Rajesh Kumar Tamada and Junpyo Hong. These collaborations have contributed to the development of innovative solutions in the field of artificial intelligence.

Conclusion

Guarav Kumar's contributions to deep neural network compression highlight his role as an influential inventor in the tech industry. His work not only advances the field of artificial intelligence but also has significant implications for healthcare technologies.

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