Grenoble, France

Marina Reyboz

This inventor holds 1 USPTO granted patent and 2 published patent applications. Top assignees: Centre National De La Recherche Scientifique, Commissariat a L'energie Atomique Et Aux Energies Alternatives, Université De Chambéry - Université Savoie Mont Blanc. Active years: 2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Marina Reyboz. Retrieved from https://idiyas.com/inventor/marina-reyboz

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 1 

Average Co-Inventor Count = 1.0

ph-index = 1


Company Filing History:


Years Active: 2026

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

Title: Marina Reyboz and Neural-Network Knowledge Transfer.

Introduction

Marina Reyboz is an inventor associated with Grenoble, France. Her patent work concerns a method for transferring knowledge from a trained artificial neural network to another neural network.

Latest Patents

The listed patent, “Device and Method for Transferring Knowledge of an Artificial Neural Network,” describes a way to generate training data from a trained network. The method begins by injecting a sample into the trained network, then reinjects pseudo samples generated from its outputs. By repeating this process, it creates multiple pseudo samples originating from the same initial sample, along with corresponding output values, for training a further neural network. Reyboz is listed as an inventor on 1 patent.

Career Highlights

Reyboz is associated with the Commissariat à l’Énergie Atomique et aux Énergies Alternatives and Université Grenoble Alpes. These organizations are connected to research and higher education in France.

Collaborations

Her listed coworkers include Miquel Angel Solinas and Stéphane Rousset.

Conclusion

Marina Reyboz’s listed invention addresses neural-network training by generating repeated pseudo samples to help transfer knowledge between artificial neural networks.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…