Mountain View, CA, United States of America

Charbel Sakr

USPTO Granted Patents = 1 

Average Co-Inventor Count = 6.0

ph-index = 1


Company Filing History:


Years Active: 2025

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

Title: Charbel Sakr: Innovator in Neural Network Optimization

Introduction

Charbel Sakr is a prominent inventor based in Mountain View, CA (US). He has made significant contributions to the field of neural networks, particularly in optimizing the processing of tensors and vectors. His innovative approach aims to reduce power consumption while maintaining computational accuracy.

Latest Patents

Charbel Sakr holds a patent titled "Optimally clipped tensors and vectors." This patent addresses the quantization of tensors and vectors processed within a neural network. The process of quantization reduces the number of bits used to represent a value, which can decrease power consumption and potentially accelerate processing. Sakr's method focuses on performing quantization without sacrificing accuracy. By utilizing quantization-aware training (QAT), he dynamically quantizes tensors using optimal clipping scalars. This approach minimizes the mean squared error (MSE) of the quantized operation, providing a more efficient solution compared to conventional techniques.

Career Highlights

Charbel Sakr is currently employed at Nvidia Corporation, where he continues to push the boundaries of technology in the field of artificial intelligence. His work has garnered attention for its innovative solutions to complex problems in neural network processing.

Collaborations

Some of Charbel's notable coworkers include Steve Haihang Dai and Brucek Kurdo Khailany. Their collaborative efforts contribute to the advancement of technology at Nvidia Corporation.

Conclusion

Charbel Sakr's contributions to the field of neural networks exemplify the importance of innovation in technology. His patent on optimally clipped tensors and vectors showcases his commitment to enhancing computational efficiency while preserving accuracy.

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