This inventor holds 1 USPTO granted patent and 5 published patent applications. Top assignee: Nvidia Corporation. 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: Thierry Tambe: Neural Network Quantization Inventor.
Introduction
Thierry Tambe is an inventor based in Cambridge, Massachusetts. His patent work concerns quantized neural network training and inference, a technique for processing neural networks using quantized data.
Latest Patents
Tambe is associated with one patent, titled “Quantized Neural Network Training and Inference.” The patent describes a computer-implemented method that receives a quantized matrix representing part of a multidimensional input tensor, along with the scale factor used to quantize it. Computational operations then use the matrix and scale factor to generate data values for part of a multidimensional output tensor. 1 patent.
Career Highlights
Tambe is associated with NVIDIA Corporation. His patent reflects work on methods for neural network computation using quantized matrices and scale factors.
Collaborations
The provided information identifies Brucek Kurdo Khailany and Steve Haihang Dai as Tambe’s coworkers.
Conclusion
Thierry Tambe’s patent focuses on quantized neural network processing, connecting his inventive work with NVIDIA Corporation and collaborators in the field.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile