Patents by Inventor Ramanujam Madhavan

Ramanujam Madhavan 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).

  • Patent number: 11568326
    Abstract: Computer-implemented systems and methods for generating and using a location sensitive ensemble classifier for classifying content includes dividing a validation data set into regions. Each region encompasses data points of the validation data set that fall within the region. A regional ensemble classifier is generated for each region based on the data points that fall within the region. A content item is then classified in at least one of a plurality of classes using the regional ensemble classifier for the region to which the content item belongs.
    Type: Grant
    Filed: January 13, 2020
    Date of Patent: January 31, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ramanujam Madhavan, Mohit Wadhwa
  • Publication number: 20210216916
    Abstract: Computer-implemented systems and methods for generating and using a location sensitive ensemble classifier for classifying content includes dividing a validation data set into regions. Each region encompasses data points of the validation data set that fall within the region. A regional ensemble classifier is generated for each region based on the data points that fall within the region. A content item is then classified in at least one of a plurality of classes using the regional ensemble classifier for the region to which the content item belongs.
    Type: Application
    Filed: January 13, 2020
    Publication date: July 15, 2021
    Inventors: Ramanujam Madhavan, Mohit Wadhwa
  • Publication number: 20200265341
    Abstract: Disclosed are systems, methods, and non-transitory computer-readable media for automatic detection of labeling errors. A classification system uses a classification model to determine a classification label for a data item and compares the classification label to a classification label assigned to the data item by a human labeler. In response to determining that the classification label determined by the classification model is different than the classification label assigned by the human labeler human labeler, the classification system determines, using a model interpretability technique, a list of features that contributed to the classification model determining the classification label for the data item, and determines, based on the list of features, a probability value indicating a likelihood that the classification label determined by the classification model properly classifies the data item.
    Type: Application
    Filed: February 18, 2019
    Publication date: August 20, 2020
    Inventors: Rushi Prafull Bhatt, Abijith Karippale Padinjareveedu, Ramanujam Madhavan