Patents by Inventor Benjamin Orth Chandler

Benjamin Orth Chandler 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).

  • Dataset augmentation based on occlusion and inpainting
    Patent number: 11017311
    Abstract: Augmenting a dataset in a machine learning classifier is disclosed. One example is a system including a training dataset with at least one training data, and a label preserving transformation including an occluder, and an inpainter. The occluder occludes a selected portion of the at least one training data. The inpainter inpaints the occluded portion of the at least one training data, where the inpainting is based on data from a portion different from the occluded portion. In one example, the augmented dataset is deployed to train a machine learning classifier.
    Type: Grant
    Filed: June 30, 2014
    Date of Patent: May 25, 2021
    Assignee: Hewlett Packard Enterprise Development LP
    Inventor: Benjamin Orth Chandler
  • Sloppy feedback loop compilation
    Patent number: 10261766
    Abstract: A system, method, and a computer-readable storage device for sloppy feedback loop compilation are described herein. For example, a dataflow application definition can be obtained. The dataflow application definition may include a feedback loop bounding a compute block. It may then be determined that the feedback loop is to be compiled as a sloppy feedback loop. The dataflow application can then be compiled as an executable object that pipelines the compute block of the dataflow application.
    Type: Grant
    Filed: August 28, 2014
    Date of Patent: April 16, 2019
    Assignee: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP
    Inventor: Benjamin Orth Chandler
  • SLOPPY FEEDBACK LOOP COMPILATION
    Publication number: 20170185387
    Abstract: A system, method, and a computer-readable storage device for sloppy feedback loop compilation are described herein. For example, a dataflow application definition can be obtained. The dataflow application definition may include a feedback loop bounding a compute block. It may then be determined that the feedback loop is to be compiled as a sloppy feedback loop. The dataflow application can then be compiled as an executable object that pipelines the compute block of the dataflow application.
    Type: Application
    Filed: August 28, 2014
    Publication date: June 29, 2017
    Applicant: Hewlett Packard Enterprise Development LP
    Inventor: Benjamin Orth Chandler
  • Dataset Augmentation Based on Occlusion and Inpainting
    Publication number: 20150379422
    Abstract: Augmenting a dataset in a machine learning classifier is disclosed. One example is a system including a training dataset with at least one training data, and a label preserving transformation including an occluder, and an inpainter. The occluder occludes a selected portion of the at least one training data. The inpainter inpaints the occluded portion of the at least one training data, where the inpainting is based on data from a portion different from the occluded portion. In one example, the augmented dataset is deployed to train a machine learning classifier.
    Type: Application
    Filed: June 30, 2014
    Publication date: December 31, 2015
    Inventor: Benjamin Orth Chandler