Patents by Inventor Ashrith Barthur

Ashrith Barthur 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).

  • ANOMALOUS BEHAVIOR DETECTION
    Publication number: 20240004742
    Abstract: A training dataset is used to train an unsupervised machine learning trained model. Corresponding gradient values are determined for a plurality of entries included in the training dataset using the trained unsupervised machine learning model. A first subset of the training dataset is selected based on the determined corresponding gradient values and a first threshold value selected from a set of threshold values. A labeled version of the selected first subset is used to train a first supervised machine learning model to detect one or more anomalies.
    Type: Application
    Filed: April 21, 2023
    Publication date: January 4, 2024
    Inventor: Ashrith Barthur
  • TIME-BASED ENSEMBLE MACHINE LEARNING MODEL
    Publication number: 20230177352
    Abstract: An input dataset is sorted into a first version of data and a second version of data. The first version of data is associated with a first period of time and the second version of data is associated with a second period of time. The second period of time is a shorter period of time than the first period of time. A first set of one or more machine learning models is generated based on the first version of data. A second set of one or more machine learning models is generated based on the second version of data. The first set of one or more machine learning models and the second set of one or more machine learning models are combined to generate an ensemble model. A prediction based on the ensemble model is outputted. The prediction indicates abnormal behavior associated with the input dataset.
    Type: Application
    Filed: July 7, 2022
    Publication date: June 8, 2023
    Inventors: SriSatish Ambati, Ashrith Barthur
  • Anomalous behavior detection
    Patent number: 11663061
    Abstract: A training dataset is used to train an unsupervised machine learning trained model. Corresponding gradient values are determined for a plurality of entries included in the training dataset using the trained unsupervised machine learning model. A first subset of the training dataset is selected based on the determined corresponding gradient values and a first threshold value selected from a set of threshold values. A labeled version of the selected first subset is used to train a first supervised machine learning model to detect one or more anomalies.
    Type: Grant
    Filed: January 31, 2019
    Date of Patent: May 30, 2023
    Assignee: H2O.ai Inc.
    Inventor: Ashrith Barthur
  • Time-based ensemble machine learning model
    Patent number: 11416751
    Abstract: An input dataset is sorted into a first version of data and a second version of data. The first version of data is associated with a first period of time and the second version of data is associated with a second period of time. The second period of time is a shorter period of time than the first period of time. A first set of one or more machine learning models is generated based on the first version of data. A second set of one or more machine learning models is generated based on the second version of data. The first set of one or more machine learning models and the second set of one or more machine learning models are combined to generate an ensemble model. A prediction based on the ensemble model is outputted. The prediction indicates abnormal behavior associated with the input dataset.
    Type: Grant
    Filed: March 27, 2018
    Date of Patent: August 16, 2022
    Assignee: H2O.ai Inc.
    Inventors: SriSatish Ambati, Ashrith Barthur
  • ANOMALOUS BEHAVIOR DETECTION
    Publication number: 20200250477
    Abstract: A training dataset is used to train an unsupervised machine learning trained model. Corresponding gradient values are determined for a plurality of entries included in the training dataset using the trained unsupervised machine learning model. A first subset of the training dataset is selected based on the determined corresponding gradient values and a first threshold value selected from a set of threshold values. A labeled version of the selected first subset is used to train a first supervised machine learning model to detect one or more anomalies.
    Type: Application
    Filed: January 31, 2019
    Publication date: August 6, 2020
    Inventor: Ashrith Barthur
  • TIME-BASED ENSEMBLE MACHINE LEARNING MODEL
    Publication number: 20180293501
    Abstract: An input dataset is sorted into a first version of data and a second version of data. The first version of data is associated with a first period of time and the second version of data is associated with a second period of time. The second period of time is a shorter period of time than the first period of time. A first set of one or more machine learning models is generated based on the first version of data. A second set of one or more machine learning models is generated based on the second version of data. The first set of one or more machine learning models and the second set of one or more machine learning models are combined to generate an ensemble model. A prediction based on the ensemble model is outputted. The prediction indicates abnormal behavior associated with the input dataset.
    Type: Application
    Filed: March 27, 2018
    Publication date: October 11, 2018
    Inventors: SriSatish Ambati, Ashrith Barthur