Patents by Inventor AbdulRahman Diaa

AbdulRahman Diaa 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).

  • Splitting neural networks on multiple edge devices to train on vertically distributed data
    Patent number: 11934487
    Abstract: One example method includes a pipeline for a distributed neural network. The pipeline includes a first phase that identifies intersecting identifiers across datasets of multiple clients in a privacy preserving manner. The second phase includes a distributed neural network that includes a data receiving portion at each of the clients and an orchestrator portion at an orchestrator. The data receiving portions and the orchestrator portions communicate forward and backward passes to perform training without revealing the raw training data.
    Type: Grant
    Filed: September 30, 2020
    Date of Patent: March 19, 2024
    Assignee: EMC IP HOLDING COMPANY LLC
    Inventors: Mohamed Abouzeid, Osama Taha Mohamed, AbdulRahman Diaa
  • MARKET BASKET ANALYSIS FOR INFANT HYBRID TECHNOLOGY DETECTION
    Publication number: 20220343350
    Abstract: One example method includes identifying emerging hybrid technologies. Datasets are data mined to identify transactions that are related to technology. Associations are generated based on the transactions and the associations are processed to identify emerging hybrid technologies from the transactions.
    Type: Application
    Filed: April 22, 2021
    Publication date: October 27, 2022
    Inventors: Mohamed Abouzeid, Ahmed Osama, Amr Abdel Aziz, Marianne Toma, Stephen J. Todd, Osama Taha Mohamed, Yaseen Moussa, Abdulrahman Diaa
  • SPLITTING NEURAL NETWORKS ON MULTIPLE EDGE DEVICES TO TRAIN ON VERTICALLY DISTRIBUTED DATA
    Publication number: 20220101054
    Abstract: One example method includes a pipeline for a distributed neural network. The pipeline includes a first phase that identifies intersecting identifiers across datasets of multiple clients in a privacy preserving manner. The second phase includes a distributed neural network that includes a data receiving portion at each of the clients and an orchestrator portion at an orchestrator. The data receiving portions and the orchestrator portions communicate forward and backward passes to perform training without revealing the raw training data.
    Type: Application
    Filed: September 30, 2020
    Publication date: March 31, 2022
    Inventors: Mohamed Abouzeid, Osama Taha Mohamed, AbdulRahman Diaa