Patents by Inventor Stephane Rousset

Stephane Rousset has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 12762425
    Abstract: A method of generating training data for transferring knowledge from a trained artificial neural network to a further artificial neural network, the method including: a) injecting a first sample into the trained artificial neural network; b) reinjecting a pseudo sample, generated based on a replicated sample present at the one or more outputs of the trained artificial neural network, into the trained artificial neural network in order to generate a new replicated sample; and c) repeating b) one or more times, wherein the training data for training the further artificial neural network includes at least two of the reinjected pseudo samples originating from the same first sample and corresponding output values generated by the trained artificial neural network.
    Type: Grant
    Filed: April 1, 2021
    Date of Patent: October 13, 2026
    Assignees: Commissariat à l'Énergie Atomique et aux Énergies Alternatives, Universite Grenoble Alpes, Centre National de la Recherche Scientifique, Université de Chambéry—Université Savoie Mont Blanc
    Inventors: Miquel Angel Solinas, Marina Reyboz, Stephane Rousset, Martial Mermillod, Clovis Galiez
  • Publication number: 20230325659
    Abstract: A method of training an artificial neural network, the method comprising: initially training a first artificial neural network with first input data and first pseudo data, wherein the first pseudo data is or was generated by a second artificial neural network in a virgin state, or by the first artificial neural network while in a virgin state; generating second pseudo data using the first artificial neural network, or using the second artificial neural network following at least partially transferring knowledge from the first artificial neural network to the second artificial neural network; and training the first artificial neural network, or another artificial neural network, with the second pseudo data and second input data.
    Type: Application
    Filed: September 8, 2021
    Publication date: October 12, 2023
    Applicants: Commissariat à I'Énergie Atomique et aux Énergies Alternatives, Universite Grenoble Alpes, Centre National de la Recherche Scientifique, Université de Chambéry - Université Savoie Mont Blanc
    Inventors: Miguel-Angel Solinas, Martial Mermillod, Marina REyboz, Stephane Rousset
  • Publication number: 20230153632
    Abstract: A method of generating training data for transferring knowledge from a trained artificial neural network to a further artificial neural network, the method including: a) injecting a first sample into the trained artificial neural network; b) reinjecting a pseudo sample, generated based on a replicated sample present at the one or more outputs of the trained artificial neural network, into the trained artificial neural network in order to generate a new replicated sample; and c) repeating b) one or more times, wherein the training data for training the further artificial neural network includes at least two of the reinjected pseudo samples originating from the same first sample and corresponding output values generated by the trained artificial neural network.
    Type: Application
    Filed: April 1, 2021
    Publication date: May 18, 2023
    Applicants: Commissariat à I'Énergie Atomique et aux Énergies Alternatives, Universite Grenoble Alpe, Centre National de la Recherche Scientifique, Université de Chambéry - Université Savoie Mont Blanc
    Inventors: Miquel Angel Solinas, Marina Reyboz, Stephane Rousset, Martial Mermillod, Clovis Galiez