Patents by Inventor Evan Randy Kirshenbaum

Evan Randy Kirshenbaum 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).

  • Count estimation via machine learning
    Patent number: 8744987
    Abstract: One or more machine learning classifiers are trained to classify cases in one or more categories using one or more sets of labeled training data. A first distribution of scores for positive cases in the training set is determined for each category, and a second distribution of scores for negative cases in the training set is determined for each category. A third distribution of scores is generated by each classifier classifying cases in a set of target data is also determined. A proportion of cases in the target set that are positive cases for a category is estimated by fitting the first distribution and the second distribution for the category to the third distribution.
    Type: Grant
    Filed: April 19, 2006
    Date of Patent: June 3, 2014
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: George Henry Forman, Henri Jacques Suermondt, Evan Randy Kirshenbaum
  • Data structure representation using hash-based directed acyclic graphs and related method
    Patent number: 7895666
    Abstract: A method for creating an embedding node. The method includes creating a first hash-based directed acyclic graph (“HDAG”) having a first node, which includes data, and creating a second HDAG having a second node that includes one or more data fields that store the first node.
    Type: Grant
    Filed: September 1, 2006
    Date of Patent: February 22, 2011
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Kave Eshghi, Evan Randy Kirshenbaum, Mark David Lillibridge
  • Multi-module genetic programming with multiple genetic data representations
    Patent number: 7424461
    Abstract: A method for genetic programming which is based on multiple genetic data component representations. Multiple genetic data component representations are determined and a solution is evolved using a set of genetic data components represented by the multiple genetic data component representations.
    Type: Grant
    Filed: June 28, 2001
    Date of Patent: September 9, 2008
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventor: Evan Randy Kirshenbaum
  • Deriving a genome representation for evolving graph structure weights
    Patent number: 6988089
    Abstract: A method for deriving a genome representation for the weights in a graph structure that increases the likelihood that solutions to substructures of the graph structure will be preserved during crossover operations. The preservation of solutions to substructures across generations of organisms may decrease the computational time when evolving to a desired solution.
    Type: Grant
    Filed: May 2, 2001
    Date of Patent: January 17, 2006
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventors: Evan Randy Kirshenbaum, Kenneth O. Stanley, Bin Zhang
  • Predicting manufacturing process failures
    Patent number: 6804570
    Abstract: A method for generating a predictor of failure of a manufacturing process. The predictor is generated by generating a candidate solution for the predictor and then determining a fitness of the candidate solution using fitness cases pertaining to the manufacturing process and a set of costs associated with the manufacturing process. The fitness may then be used to formulate a next generation of candidate solutions for a design method modeled on evolution.
    Type: Grant
    Filed: February 4, 2002
    Date of Patent: October 12, 2004
    Assignee: Hewlett-Packard Development Company, L.P.
    Inventor: Evan Randy Kirshenbaum
  • Predicting manufacturing process failures
    Publication number: 20030149499
    Abstract: A method for generating a predictor of failure of a manufacturing process. The predictor is generated by generating a candidate solution for the predictor and then determining a fitness of the candidate solution using fitness cases pertaining to the manufacturing process and a set of costs associated with the manufacturing process. The fitness may then be used to formulate a next generation of candidate solutions for a design method modeled on evolution.
    Type: Application
    Filed: February 4, 2002
    Publication date: August 7, 2003
    Inventor: Evan Randy Kirshenbaum
  • Deriving a genome representation for evolving graph structure weights
    Publication number: 20030033264
    Abstract: A method for deriving a genome representation for the weights in a graph structure that increases the likelihood that solutions to substructures of the graph structure will be preserved during crossover operations. The preservation of solutions to substructures across generations of organisms may decrease the computational time when evolving to a desired solution.
    Type: Application
    Filed: May 2, 2001
    Publication date: February 13, 2003
    Inventors: Evan Randy Kirshenbaum, Kenneth O. Stanley, Bin Zhang
  • Multi-module genetic Programming with multiple genetic data representations
    Publication number: 20030004904
    Abstract: A method for genetic programming which is based on multiple genetic data component representations. Multiple genetic data component representations are determined and a solution is evolved using a set of genetic data components represented by the multiple genetic data component representations.
    Type: Application
    Filed: June 28, 2001
    Publication date: January 2, 2003
    Inventor: Evan Randy Kirshenbaum