Patents by Inventor John Alejandro Izquierdo

John Alejandro Izquierdo 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).

  • Staged training of neural networks for improved time series prediction performance
    Patent number: 10740395
    Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.
    Type: Grant
    Filed: December 26, 2019
    Date of Patent: August 11, 2020
    Assignee: SAS INSTITUTE INC.
    Inventors: Henry Gabriel Victor Bequet, Jacques Rioux, John Alejandro Izquierdo, Huina Chen, Juan Du
  • Staged training of neural networks for improved time series prediction performance
    Patent number: 10650045
    Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.
    Type: Grant
    Filed: August 30, 2019
    Date of Patent: May 12, 2020
    Assignee: SAS INSTITUTE INC.
    Inventors: Henry Gabriel Victor Bequet, Jacques Rioux, John Alejandro Izquierdo, Huina Chen, Juan Du
  • STAGED TRAINING OF NEURAL NETWORKS FOR IMPROVED TIME SERIES PREDICTION PERFORMANCE
    Publication number: 20200133977
    Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.
    Type: Application
    Filed: December 26, 2019
    Publication date: April 30, 2020
    Inventors: Henry Gabriel Victor Bequet, Jacques Rioux, John Alejandro Izquierdo, Huina Chen, Juan Du
  • STAGED TRAINING OF NEURAL NETWORKS FOR IMPROVED TIME SERIES PREDICTION PERFORMANCE
    Publication number: 20190384790
    Abstract: An apparatus includes a processor to: train a first neural network of a chain to generate first configuration data including first trained parameters, wherein the chain performs an analytical function generating a set of output values from a set of input values, each neural network has inputs to receive the set of input values and outputs to output a portion of the set of output values, and the neural networks are ordered from the first at the head to a last neural network at the tail, and are interconnected so that each neural network additionally receives the outputs of a preceding neural network; train, using the first configuration data, a next neural network in the chain ordering to generate next configuration data including next trained parameters; and use at least the first and next configuration data and data indicating the interconnections to instantiate the chain to perform the analytical function.
    Type: Application
    Filed: August 30, 2019
    Publication date: December 19, 2019
    Inventors: Henry Gabriel Victor Bequet, Jacques Rioux, John Alejandro Izquierdo, Huina Chen, Juan Du