Patents by Inventor Karthikeyan Natesan Ramamurthy

Karthikeyan Natesan Ramamurthy 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: 20210089941
    Abstract: Techniques for sanitization of machine learning (ML) models are provided. A first ML model is received, along with clean training data. A path is trained between the first ML model and a second ML model using the clean training data. A sanitized ML model is generated based on at least one point on the trained path. One or more ML functionalities are then facilitated using the sanitized ML model.
    Type: Application
    Filed: December 4, 2019
    Publication date: March 25, 2021
    Inventors: Pin-Yu Chen, Payel Das, Karthikeyan Natesan Ramamurthy, Pu Zhao
  • Publication number: 20200202599
    Abstract: A method and system of stitching a plurality of image views of a scene, including grouping matched points of interest in a plurality of groups, and determining a similarity transformation with smallest rotation angle for each grouping of the matched points. The method further includes generating virtual matching points on non-overlapping area of the plurality of image views and generating virtual matching points on overlapping area for each of the plurality of image views.
    Type: Application
    Filed: January 20, 2020
    Publication date: June 25, 2020
    Inventors: Chung-Ching LIN, Sharathchandra U. Pankanti, Karthikeyan Natesan Ramamurthy, Aleksandr Y. Aravkin, John R. Smith
  • Publication number: 20200184350
    Abstract: A post-processing method, system, and computer program product for post-hoc improvement of instance-level and group-level prediction metrics, including training a bias detector that learns to detect a sample that has an individual bias greater than a predetermined individual bias threshold value with constraints on a group bias, applying the bias detector on a run-time sample to select a biased sample in the run-time sample having a bias greater than the predetermined individual bias threshold bias value, and suggesting a de-biased prediction for the biased sample.
    Type: Application
    Filed: December 10, 2018
    Publication date: June 11, 2020
    Inventors: Manish Bhide, pranay Lohia, Karthikeyan Natesan Ramamurthy, Ruchir puri, Diptikalyan Saha, Kush Raj Varshney
  • Patent number: 10553005
    Abstract: A method and system of stitching a plurality of image views of a scene, including grouping matched points of interest in a plurality of groups, and determining a similarity transformation with smallest rotation angle for each grouping of the matched points. The method further includes generating virtual matching points on non-overlapping area of the plurality of image views and generating virtual matching points on overlapping area for each of the plurality of image views.
    Type: Grant
    Filed: February 10, 2017
    Date of Patent: February 4, 2020
    Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATION
    Inventors: Chung-Ching Lin, Sharathchandra U. Pankanti, Karthikeyan Natesan Ramamurthy, Aleksandr Y. Aravkin, John R. Smith
  • Publication number: 20190333155
    Abstract: A method, computer system, and a computer program product for generating and reporting a plurality of health insurance cost predictions via private transfer learning is provided. The present invention may include retrieving a set of source data, and a set of target data. The present invention may then include creating and anonymizing a plurality of source data sets, and at least one target data set. The present invention may further include generating one or more source learner models, and a target learner model. The present invention may then include combining the one or more generated source learner models and the generated target learner model to generate a transfer learner. The present invention may further include generating a prediction based on the generated transfer learner.
    Type: Application
    Filed: April 27, 2018
    Publication date: October 31, 2019
    Inventors: Karthikeyan Natesan Ramamurthy, Emily A. Ray, Dennis Wei, Gigi Y.C. Yuen-Reed
  • Publication number: 20190179943
    Abstract: Modularized data processing systems and methods for its use are provided. Processing a current job can reuse data generated for a previously processed job to the extent the two share parameter configurations. Similarly, outputs of processing modules generated during processing the previously processed job can be used as inputs to processing modules processing a current job, if the two jobs share some parameter configurations.
    Type: Application
    Filed: December 8, 2017
    Publication date: June 13, 2019
    Inventors: JINGWEI YANG, Shilpa N. Mahatma, RACHITA CHANDRA, Kevin N. Tran, Dennis Wei, Karthikeyan NATESAN RAMAMURTHY, Gigi Yuen-Reed
  • Publication number: 20190172564
    Abstract: A system may predict costs for a set of members by building and using a predictive pipeline. The pipeline may be built using a set of historical data for training members. A set of member-level features can be identified by performing empirical testing on the set of historical data. The trained configurable predictive pipeline can generate a set of predictive data for each member, using historical test data for a set of testing members. The system can then generate a predictive report for each set of predictive data.
    Type: Application
    Filed: December 5, 2017
    Publication date: June 6, 2019
    Inventors: Rachita Chandra, Vijay S. Iyengar, Dmitriy A. Katz, Karthikeyan Natesan Ramamurthy, Emily A. Ray, Moninder Singh, Dennis Wei, Gigi Y. C. Yuen-Reed, Kevin N. Tran
  • Publication number: 20170301119
    Abstract: A method and system of stitching a plurality of image views of a scene, including grouping matched points of interest in a plurality of groups, and determining a similarity transformation with smallest rotation angle for each grouping of the matched points. The method further includes generating virtual matching points on non-overlapping area of the plurality of image views and generating virtual matching points on overlapping area for each of the plurality of image views.
    Type: Application
    Filed: February 10, 2017
    Publication date: October 19, 2017
    Inventors: Chung-Ching Lin, Sharathchandra U. Pankanti, Karthikeyan Natesan Ramamurthy, Aleksandr Y. Aravkin, John R. Smith
  • Publication number: 20170140393
    Abstract: A system, method and program product for cost attribution using multiple factors, in which transactional data sets from two or more time periods are analyzed based on multiple potential factors in the data sets that can be correlated to cost. The potential factors are systematically analyzed to identify a set of cost factors and compute the cost impact for each cost factor. An infrastructure is disclosed having a data selection system; a potential factors system; a factor hierarchy system; an actionability class system; a factor processing system and a cost factor reporting system for providing the cost impact of the set of cost factors based on analysis of the transactional data sets.
    Type: Application
    Filed: November 13, 2015
    Publication date: May 18, 2017
    Inventors: Dmitriy A. Katz-Rogozhnikov, Aleksandra Mojsilovic, Karthikeyan Natesan Ramamurthy, Dennis Wei, Gigi Y. Yuen-Reed
  • Patent number: 9569874
    Abstract: A method and a system of stitching a plurality of views of a scene, the method including extracting points of interest in each view to include a point set from each of the plurality of image views of the scene, matching the points of interest and reducing an outlier, grouping the matched points of interest in a plurality of groups, determining a similarity transformation with a smallest rotation angle for each grouping of the match points, generating virtual matching points on a non-overlapping area of the plurality of image views, generating virtual matching points on an overlapping area for each of the plurality of image views, and calculating piecewise projective transformations for the plurality of image views.
    Type: Grant
    Filed: June 5, 2015
    Date of Patent: February 14, 2017
    Assignee: International Business Machines Corporation
    Inventors: Chung-Ching Lin, Sharathchandra U. Pankanti, Karthikeyan Natesan Ramamurthy, Aleksandr Y. Aravkin, John R. Smith
  • Publication number: 20160358355
    Abstract: A method and a system of stitching a plurality of views of a scene, the method including extracting points of interest in each view to include a point set from each of the plurality of image views of the scene, matching the points of interest and reducing an outlier, grouping the matched points of interest in a plurality of groups, determining a similarity transformation with a smallest rotation angle for each grouping of the match points, generating virtual matching points on a non-overlapping area of the plurality of image views, generating virtual matching points on an overlapping area for each of the plurality of image views, and calculating piecewise projective transformations for the plurality of image views.
    Type: Application
    Filed: June 5, 2015
    Publication date: December 8, 2016
    Inventors: Chung-Ching Lin, Sharathchandra U. Pankanti, Karthikeyan Natesan Ramamurthy, Aleksandr Y. Aravkin, John R. Smith
  • Publication number: 20160321748
    Abstract: Exemplary embodiments of the present invention provide a method of health insurance market risk assessment including receiving first data including demographic and cost data for members of a health insurance plan in a current market, receiving second data including demographic data for the current market, and receiving third data including demographic data for a new market. The first to third data are used to transform a distribution of the plan members to account for differences between the current and new market demographic data and to estimate probabilities of enrollment in the new market. A statistical model is learned to predict risk in the new market using the transformed distribution and the estimated probabilities. The statistical model is used to determine risk of entering the new market.
    Type: Application
    Filed: April 29, 2015
    Publication date: November 3, 2016
    Inventors: Shilpa Mahatma, Aleksandra Mojsilovic, Karthikeyan Natesan Ramamurthy, Kush R. Varshney, Dennis Wei, Gigi Yuen-Reed