Patents by Inventor Alejandro de la Calle

Alejandro de la Calle 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).

  • Initialization of classification layers in neural networks
    Patent number: 11676034
    Abstract: Example methods disclosed herein to initialize classification vectors of a neural network include ranking a plurality of classes to be represented by the classification vectors based on respective numbers of instances of training data associated with corresponding ones of the classes. Disclosed example methods also include initializing the classification vectors to span a classification space corresponding to the classes. Disclosed example methods further include assigning respective ones of the classes to corresponding ones of the classification vectors based on the ranking of the classes.
    Type: Grant
    Filed: April 28, 2020
    Date of Patent: June 13, 2023
    Assignee: The Nielsen Company (US), LLC
    Inventors: Emilio Almazán, Javier Tovar Velasco, Alejandro de la Calle
  • METHODS, SYSTEMS, APPARATUS AND ARTICLES OF MANUFACTURE TO APPLY A REGULARIZATION LOSS IN MACHINE LEARNING MODELS
    Publication number: 20220092424
    Abstract: Methods, systems, apparatus and articles of manufacture are disclosed herein to apply a regularization loss in machine learning models.
    Type: Application
    Filed: September 17, 2021
    Publication date: March 24, 2022
    Inventors: Emilio Almazán Manzanares, Javier Tovar Velasco, Alejandro de la Calle
  • INITIALIZATION OF CLASSIFICATION LAYERS IN NEURAL NETWORKS
    Publication number: 20200410320
    Abstract: Example methods disclosed herein to initialize classification vectors of a neural network include ranking a plurality of classes to be represented by the classification vectors based on respective numbers of instances of training data associated with corresponding ones of the classes. Disclosed example methods also include initializing the classification vectors to span a classification space corresponding to the classes. Disclosed example methods further include assigning respective ones of the classes to corresponding ones of the classification vectors based on the ranking of the classes.
    Type: Application
    Filed: April 28, 2020
    Publication date: December 31, 2020
    Inventors: Emilio Almazán, Javier Tovar Velasco, Alejandro de la Calle