Patents by Inventor Florian Strub

Florian Strub 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).

  • Self-supervised representation learning using bootstrapped latent representations
    Patent number: 12699893
    Abstract: A computer-implemented method of training a neural network. The method comprises processing a first transformed view of a training data item, e.g. an image, with a target neural network to generate a target output, processing a second transformed view of the training data item, e.g. image, with an online neural network to generate a prediction of the target output, updating parameters of the online neural network to minimize an error between the prediction of the target output and the target output, and updating parameters of the target neural network based on the parameters of the online neural network. The method can effectively train an encoder neural network without using labelled training data items, and without using a contrastive loss, i.e. without needing “negative examples” which comprise transformed views of different data items.
    Type: Grant
    Filed: June 4, 2021
    Date of Patent: August 4, 2026
    Assignee: GDM Holding LLC
    Inventors: Jean-Bastien François Laurent Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Remi Munos, Michal Valko
  • CONTRASTIVE LEARNING USING POSITIVE PSEUDO LABELS
    Publication number: 20250342355
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network to perform a machine learning task on one or more received inputs by using a hybrid training dataset with a semi-supervised learning technique. The hybrid training dataset includes multiple unlabeled training inputs and multiple labeled training inputs and, in some cases, more unlabeled training inputs than labeled training inputs.
    Type: Application
    Filed: May 19, 2023
    Publication date: November 6, 2025
    Inventors: Jovana Mitrovic, Matko Bosnjak, Pierre Richemond, Nenad Tomasev, Florian Strub, Jacob Charles Walker, Felix George Hill, Lars Buesing, Razvan Pascanu, Charles Blundell
  • SELF-SUPERVISED REPRESENTATION LEARNING USING BOOTSTRAPPED LATENT REPRESENTATIONS
    Publication number: 20210383225
    Abstract: A computer-implemented method of training a neural network. The method comprises processing a first transformed view of a training data item, e.g. an image, with a target neural network to generate a target output, processing a second transformed view of the training data item, e.g. image, with an online neural network to generate a prediction of the target output, updating parameters of the online neural network to minimize an error between the prediction of the target output and the target output, and updating parameters of the target neural network based on the parameters of the online neural network. The method can effectively train an encoder neural network without using labelled training data items, and without using a contrastive loss, i.e. without needing “negative examples” which comprise transformed views of different data items.
    Type: Application
    Filed: June 4, 2021
    Publication date: December 9, 2021
    Inventors: Jean-Bastien François Laurent Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre Richemond, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Remi Munos, Michal Valko