This inventor holds 1 USPTO granted patent. Top assignee: Samsung Electronics Ltd.. Active years: 2026.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile
Company Filing History:
Years Active: 2026
Title: Prasen Kumar Sharma: Inventor in Deep Neural Network Quantization
Introduction
Prasen Kumar Sharma is an inventor based in Karnataka, India. His patent work concerns methods for quantizing deep neural network (DNN) models in electronic devices.
Latest Patents
Sharma is associated with 1 patent, titled “Method and Electronic Device for Quantizing DNN Model.” The invention describes estimating the activation range of each DNN layer using self-generated data, such as retro images, audio, or video, and/or a sensitivity index for each layer. The electronic device then quantizes the model based on the activation ranges and/or sensitivity indices, assigning dynamic bit precision to each channel in each layer.
Career Highlights
Sharma is associated with Samsung Electronics Ltd. His patent reflects work on adapting quantization to the characteristics of individual DNN layers and channels.
Collaborations
Raja Kumar and Arun Abraham are identified as Sharma’s coworkers. The available information does not specify their roles in the patent or their particular contributions.
Conclusion
Prasen Kumar Sharma’s patent focuses on layer- and channel-aware DNN quantization, an approach intended to support model implementation in electronic devices.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile