This inventor holds 1 USPTO granted patent and 1 published patent application. Top assignee: Qualcomm Incorporated. 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: Romain Lepert and Machine Learning for Netlist Design.
Introduction
Romain Lepert is an inventor based in Amsterdam, Netherlands. His patent work concerns applying machine learning to the evaluation of electronic circuit designs.
Latest Patents
Lepert is associated with 1 patent, titled “Machine Learning for Netlist Design.” The disclosed techniques access a directed graph representing an electrical circuit’s netlist, select a node corresponding to a register, and generate a subgraph that captures the register’s connectivity cone. A trained machine-learning encoder then produces a functional embedding of that subgraph, which is used to predict a performance characteristic of the netlist design.
Career Highlights
Lepert is associated with Qualcomm Incorporated. His patent reflects work at the intersection of electronic design and machine learning, using circuit connectivity information to support performance prediction.
Collaborations
Gokce Sarar is identified as Lepert’s coworker. The provided information does not specify their particular projects or contributions.
Conclusion
Romain Lepert’s patent highlights a machine-learning approach to evaluating netlist designs and predicting circuit performance.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile