Patents by Inventor Alec M. Zimmer

Alec M. Zimmer 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).

  • Augmenting incomplete training datasets for use in a machine learning system
    Patent number: 11080618
    Abstract: Systems and methods for augmenting incomplete training dataset for use in a machine learning system are described herein. In an embodiment, a server computer receives a plurality of input training datasets including one or more incomplete input training datasets and one or more complete datasets which contain one or more failure training datasets, the incomplete input training datasets comprising a plurality of parameters. Using the one or more failure training datasets, the server computer generates temporal failure data describing a likelihood of failure of an item as a function of time. Using the one or more complete training datasets, the server computer generates parameter specific likelihoods of failure of an item. The server computer augments the one or more incomplete input training datasets using the temporal failure data and/or the parameter specific likelihoods of failure to create one or more augmented training datasets.
    Type: Grant
    Filed: November 7, 2017
    Date of Patent: August 3, 2021
    Assignee: Upstart Network, Inc.
    Inventors: Brandon Ray Kam, Viraj Navkal, Grant Schneider, Paul Gu, Alec M. Zimmer
  • AUGMENTING INCOMPLETE TRAINING DATASETS FOR USE IN A MACHINE LEARNING SYSTEM
    Publication number: 20190138941
    Abstract: Systems and methods for augmenting incomplete training dataset for use in a machine learning system are described herein. In an embodiment, a server computer receives a plurality of input training datasets including one or more incomplete input training datasets and one or more complete datasets which contain one or more failure training datasets, the incomplete input training datasets comprising a plurality of parameters. Using the one or more failure training datasets, the server computer generates temporal failure data describing a likelihood of failure of an item as a function of time. Using the one or more complete training datasets, the server computer generates parameter specific likelihoods of failure of an item. The server computer augments the one or more incomplete input training datasets using the temporal failure data and/or the parameter specific likelihoods of failure to create one or more augmented training datasets.
    Type: Application
    Filed: November 7, 2017
    Publication date: May 9, 2019
    Inventors: Brandon Ray Kam, Viraj Navkal, Grant Schneider, Paul Gu, Alec M. Zimmer