Patents by Inventor Thomas Doerk

Thomas Doerk 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).

  • Decision-based data compression by means of deep learning technologies
    Patent number: 10714058
    Abstract: Data may be handled based on compressibility (i.e., whether the data may be further compressed or is not further compressible). A supervised learning model may be trained using a set of known further compressible data and a set of known non-compressible data. Using these data sets, the model may generate weighting factors and bias for the particular data sets. The trained model may then be used to evaluate a set of unclassified data.
    Type: Grant
    Filed: January 14, 2020
    Date of Patent: July 14, 2020
    Assignee: International Business Machines Corporation
    Inventors: Michael Diederich, Thomas Doerk, Thorsten Muehge, Erik Rueger
  • DECISION-BASED DATA COMPRESSION BY MEANS OF DEEP LEARNING TECHNOLOGIES
    Publication number: 20200152158
    Abstract: Data may be handled based on compressibility (i.e., whether the data may be further compressed or is not further compressible). A supervised learning model may be trained using a set of known further compressible data and a set of known non-compressible data. Using these data sets, the model may generate weighting factors and bias for the particular data sets. The trained model may then be used to evaluate a set of unclassified data.
    Type: Application
    Filed: January 14, 2020
    Publication date: May 14, 2020
    Inventors: Michael Diederich, Thomas Doerk, Thorsten Muehge, Erik Rueger
  • Decision-based data compression by means of deep learning technologies
    Patent number: 10586516
    Abstract: Data may be handled based on compressibility (i.e., whether the data may be further compressed or is not further compressible). A supervised learning model may be trained using a set of known further compressible data and a set of known non-compressible data. Using these data sets, the model may generate weighting factors and bias for the particular data sets. The trained model may then be used to evaluate a set of unclassified data.
    Type: Grant
    Filed: March 22, 2019
    Date of Patent: March 10, 2020
    Assignee: International Business Machines Corporation
    Inventors: Michael Diederich, Thomas Doerk, Thorsten Muehge, Erik Rueger
  • DECISION-BASED DATA COMPRESSION BY MEANS OF DEEP LEARNING TECHNOLOGIES
    Publication number: 20190221192
    Abstract: Data may be handled based on compressibility (i.e., whether the data may be further compressed or is not further compressible). A supervised learning model may be trained using a set of known further compressible data and a set of known non-compressible data. Using these data sets, the model may generate weighting factors and bias for the particular data sets. The trained model may then be used to evaluate a set of unclassified data.
    Type: Application
    Filed: March 22, 2019
    Publication date: July 18, 2019
    Inventors: Michael Diederich, Thomas Doerk, Thorsten Muehge, Erik Rueger
  • Decision-based data compression by means of deep learning technologies
    Patent number: 10276134
    Abstract: Data may be handled based on compressibility (i.e., whether the data may be further compressed or is not further compressible). A supervised learning model may be trained using a set of known further compressible data and a set of known non-compressible data. Using these data sets, the model may generate weighting factors and bias for the particular data sets. The trained model may then be used to evaluate a set of unclassified data.
    Type: Grant
    Filed: March 22, 2017
    Date of Patent: April 30, 2019
    Assignee: International Business Machines Corporation
    Inventors: Michael Diederich, Thomas Doerk, Thorsten Muehge, Erik Rueger
  • DECISION-BASED DATA COMPRESSION BY MEANS OF DEEP LEARNING TECHNOLOGIES
    Publication number: 20180277068
    Abstract: Data may be handled based on compressibility (i.e., whether the data may be further compressed or is not further compressible). A supervised learning model may be trained using a set of known further compressible data and a set of known non-compressible data. Using these data sets, the model may generate weighting factors and bias for the particular data sets. The trained model may then be used to evaluate a set of unclassified data.
    Type: Application
    Filed: March 22, 2017
    Publication date: September 27, 2018
    Inventors: Michael Diederich, Thomas Doerk, Thorsten Muehge, Erik Rueger
  • Data Integrity In Deduplicated Block Storage Environments
    Publication number: 20160092137
    Abstract: Methods and apparatuses for maintaining data integrity in deduplicated storage environments. A processor receives a request to write a first block of data to a storage device. A processor compares the first block of data to a second block of data, wherein the second block is stored on the storage device. A processor writes the first block of data to the storage device based, at least in part, on the first block of data matching the second block of data and an amount of pointers to the second block of data being above a predetermined amount.
    Type: Application
    Filed: September 25, 2014
    Publication date: March 31, 2016
    Inventors: Thomas Doerk, Itzhack Goldberg, Thorsten Muehge, Erik Rueger, Neil Sondhi