Patents by Inventor John Eberstein

John Eberstein 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).

  • DISPARITY MITIGATION IN MACHINE LEARNING-BASED PREDICTIONS FOR DISTINCT CLASSES OF DATA USING DERIVED INDISCERNIBILITY CONSTRAINTS DURING NEURAL NETWORK TRAINING
    Publication number: 20240135186
    Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine
    Type: Application
    Filed: December 27, 2023
    Publication date: April 25, 2024
    Applicant: Fairness-as-a-Service, Inc.
    Inventors: John Wickens-Lamb Merrill, Kareem Saleh, Mark Eberstein
  • Disparity mitigation in machine learning-based predictions for distinct classes of data using derived indiscernibility constraints during neural network training
    Patent number: 11934960
    Abstract: A system and method includes generating approximate distributions for distinct classes of data samples; computing a first partial Jensen-Shannon (JS) divergence and a second partial JS divergence based on the approximate distribution of the disparity affected class of data samples with reference to the approximate distribution of the control class of data samples; computing a disparity divergence based on the first partial JS divergence and the second partial JS divergence; generating a distribution-matching term based on the disparity divergence, wherein the distribution-matching term mitigates an inferential disparity between the control class of data samples and the disparity affected class of data samples during a training of an unconstrained artificial neural network; constructing a disparity-constrained loss function based on augmenting a target loss function with the distribution-matching term; and transforming the unconstrained ANN to a disparity-constrained ANN based on a training of the unconstraine
    Type: Grant
    Filed: May 1, 2023
    Date of Patent: March 19, 2024
    Assignee: Fairness-as-a-Service
    Inventors: John Wickens-Lamb Merrill, Kareem Saleh, Mark Eberstein
  • Thermal-nucleak powered rocket using non-cryogenic propellant
    Publication number: 20170129628
    Abstract: The invention comprises a space ship, which commutes between earth orbit and lunar orbit, and is powered by a rocket engine, using superheated steam, or other non-cryogenic propellant, where the propellant is heated in a conventional uranium nuclear reactor.
    Type: Application
    Filed: November 3, 2016
    Publication date: May 11, 2017
    Inventor: IGOR JOHN EBERSTEIN
  • Portable electronic device stand
    Patent number: D671546
    Type: Grant
    Filed: May 25, 2012
    Date of Patent: November 27, 2012
    Inventors: John Eberstein, Michael Iacono