Patents by Inventor Gi Ju JUNG

Gi Ju JUNG 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).

  • Stuck-at fault mitigation method for ReRAM-based deep learning accelerators
    Patent number: 11714727
    Abstract: A stuck-at fault mitigation method for resistive random access memory (ReRAM)-based deep learning accelerators, includes: confirming a distorted output value (Y0) due to a stuck-at fault (SAF) by using a correction data set in a pre-trained deep learning network, by means of ReRAM-based deep learning accelerator hardware; updating an average (?) and a standard deviation (?) of a batch normalization (BN) layer by using the distorted output value (Y0), by means of the ReRAM-based deep learning accelerator hardware; folding the batch normalization (BN) layer in which the average (?) and the standard deviation (?) are updated into a convolution layer or a fully-connected layer, by means of the ReRAM-based deep learning accelerator hardware; and deriving a normal output value (Y1) by using the deep learning network in which the batch normalization (BN) layer is folded, by means of the ReRAM-based deep learning accelerator hardware.
    Type: Grant
    Filed: January 21, 2022
    Date of Patent: August 1, 2023
    Assignees: UNIST ACADEMY-INDUSTRY RESEARCH CORPORATION, THE REGENTS OF THE UNIVERSITY OF CALIFORNIA, KING ABDULLAH UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Jong Eun Lee, Su Gil Lee, Gi Ju Jung, Mohammed Fouda, Fadi Kurdahi, Ahmed M. Eltawil
  • STUCK-AT FAULT MITIGATION METHOD FOR RERAM-BASED DEEP LEARNING ACCELERATORS
    Publication number: 20220245038
    Abstract: A stuck-at fault mitigation method for resistive random access memory (ReRAM)-based deep learning accelerators, includes: confirming a distorted output value (Y0) due to a stuck-at fault (SAF) by using a correction data set in a pre-trained deep learning network, by means of ReRAM-based deep learning accelerator hardware; updating an average (?) and a standard deviation (?) of a batch normalization (BN) layer by using the distorted output value (Y0), by means of the ReRAM-based deep learning accelerator hardware; folding the batch normalization (BN) layer in which the average (?) and the standard deviation (?) are updated into a convolution layer or a fully-connected layer, by means of the ReRAM-based deep learning accelerator hardware; and deriving a normal output value (Y1) by using the deep learning network in which the batch normalization (BN) layer is folded, by means of the ReRAM-based deep learning accelerator hardware.
    Type: Application
    Filed: January 21, 2022
    Publication date: August 4, 2022
    Applicants: UNIST Academy-Industry Research Corporation, THE REGENTS OF THE UNIVERSITY OF CALIFORNIA, KING ABDULLAH UNIVERSITY OF SCIENCE AND TECHNOLOGY
    Inventors: Jong Eun LEE, Su Gil LEE, Gi Ju JUNG, Mohammed FOUDA, Fadi KURDAHI, Ahmed M. ELTAWIL