Patents by Inventor Jerome L. Quinn

Jerome L. Quinn 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).

  • Publication number: 20230267301
    Abstract: One or more computer processors responsive to neural network run-time, reduce one or more sets of maximum activations along a hidden dimension respectively associated with one or more activation tensors and one or more layers of a neural network. The one or more computer processors compute an interquartile range (IQR) clip threshold for each reduced set for each sequence dimension in the neural network. The one or more computer processors clip one or more activations based on respective computed IQR clip thresholds. The one or more computer processors quantize the clipped activations.
    Type: Application
    Filed: February 23, 2022
    Publication date: August 24, 2023
    Inventors: YOUSEF EL-KURDI, Jerome L Quinn, Robert Todd Ward
  • Patent number: 11080341
    Abstract: The present application relates to systems for generating new variants from an existing corpus of documents and methods for using the same. The systems and methods generally comprise a corpus of documents and one or more types of variety provided by a user. The system generates one or more documents that are variants of the documents in the corpus of documents.
    Type: Grant
    Filed: June 29, 2018
    Date of Patent: August 3, 2021
    Assignee: International Business Machines Corporation
    Inventors: Nicholas S. Kersting, Michael P. Perrone, Jerome L. Quinn
  • Publication number: 20200004828
    Abstract: The present application relates to systems for generating new variants from an existing corpus of documents and methods for using the same. The systems and methods generally comprise a corpus of documents and one or more types of variety provided by a user. The system generates one or more documents that are variants of the documents in the corpus of documents.
    Type: Application
    Filed: June 29, 2018
    Publication date: January 2, 2020
    Inventors: Nicholas S. Kersting, Michael P. Perrone, Jerome L. Quinn
  • Patent number: 7788088
    Abstract: A method includes applying at least one tag to at least one data element stored in a database the tag having at least one associated rule, utilizing the at least one associated rule to generate at least one variant of the data element, and storing the at least one variant in the database.
    Type: Grant
    Filed: January 11, 2006
    Date of Patent: August 31, 2010
    Assignee: International Business Machines Corporation
    Inventors: William J. Ablondi, Vaibhava Goel, Ea-Ee Jan, Benoit Emmanuel Maison, Jerome L. Quinn, Karthik Visweswariah
  • Publication number: 20080215618
    Abstract: A method includes applying at least one tag to at least one data element stored in a database the tag having at least one associated rule, utilizing the at least one associated rule to generate at least one variant of the data element, and storing the at least one variant in the database.
    Type: Application
    Filed: April 3, 2008
    Publication date: September 4, 2008
    Inventors: William J. Ablondi, Vaibhava Goel, Ea-Ee Jan, Benoit Emmanuel Maison, Jerome L. Quinn, Karthik Visweswariah
  • Patent number: 6889219
    Abstract: A method of tuning a decision network can include a series of steps. The steps can include identifying a deviation between a correct interpretation of a data item and an incorrect interpretation of the data item. In a decision network including a hierarchical set of nodes and leaves, a path of traversed nodes in the decision network resulting in the deviation can be determined. The nodes can correspond to queries. A measure of goodness at a node in the path can be calculated using at least one new query as a replacement for an existing query to determine whether the measure of goodness improves using the new query compared to the old query. If the measure of goodness improves, at least one new query can be selected and the decision network can be regrown from the node down through the leaves using the at least one new query at the node.
    Type: Grant
    Filed: January 22, 2002
    Date of Patent: May 3, 2005
    Assignee: International Business Machines Corporation
    Inventors: Mark E. Epstein, Jerome L. Quinn
  • Publication number: 20030140018
    Abstract: A method of tuning a decision network can include a series of steps. The steps can include identifying a deviation between a correct interpretation of a data item and an incorrect interpretation of the data item. In a decision network including a hierarchical set of nodes and leaves, a path of traversed nodes in the decision network resulting in the deviation can be determined. The nodes can correspond to queries. A measure of goodness at a node in the path can be calculated using at least one new query as a replacement for an existing query to determine whether the measure of goodness improves using the new query compared to the old query. If the measure of goodness improves, at least one new query can be selected and the decision network can be regrown from the node down through the leaves using the at least one new query at the node.
    Type: Application
    Filed: January 22, 2002
    Publication date: July 24, 2003
    Applicant: International Business Machines Corporation
    Inventors: Mark E. Epstein, Jerome L. Quinn