Patents by Inventor Tsung-Yi Ho

Tsung-Yi Ho 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).

  • Publication number: 20250053802
    Abstract: Aspects of the invention include techniques for improving the accuracy of access-limited neural network inference in low-voltage regimes. A non-limiting example method includes training a first machine learning model to perform input transformation for reducing low-voltage bit errors for a deep neural network operating in a low-voltage regime. The training includes inputting training data into the first machine learning model such that, in response, the first machine learning model produces transformed training data; inputting the transformed training data into a clean machine learning model and into perturbed machine learning models, the perturbed machine learning models being generated by applying random bit errors to the clean machine learning model; and optimizing the first machine learning model based on a comparison of output of the clean machine learning model and of the perturbed machine learning models compared to groundtruth labels for the training data.
    Type: Application
    Filed: August 11, 2023
    Publication date: February 13, 2025
    Inventors: Pin-Yu Chen, Nandhini Chandramoorthy, Karthik V. Swaminathan, Pradip Bose, Hao-Lun Sun, Lei Hsiung, Tsung-Yi Ho
  • Publication number: 20240420455
    Abstract: Techniques regarding generating a synthetic dataset of objects are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can include a defining component that can define a tractable forward process associated with a diffusion model, with defining the tractable forward process including inputting noise to compromise training data, resulting in compromised training data. The computer executable components can further include a training component that, using the compromised training data, trains the diffusion model to reverse process the tractable forward process, wherein the training results in a compromised diffusion model.
    Type: Application
    Filed: August 18, 2023
    Publication date: December 19, 2024
    Inventors: Pin-Yu Chen, I-Hsin Chung, Bo Wu, Chuang Gan, Tsung-Yi Ho, Sheng-Yen Chou
  • Publication number: 20240412074
    Abstract: Some embodiments of the present disclosure are directed to systems, computer-readable media, and computer-implemented methods for neural network training. Some embodiments are directed to determining an attack order schedule for the data sample that includes a plurality of adversarial perturbation attacks associated with the data sample, and performing a composite adversarial attack process against the data set using the determined attack order schedule to generate a perturbed data sample for the data sample. Other embodiments may be disclosed or claimed.
    Type: Application
    Filed: June 8, 2023
    Publication date: December 12, 2024
    Inventors: Pin-Yu Chen, I-Hsin Chung, Bo Wu, Chuang Gan, Lei Hsiung, Yun-Yun Tsai, Tsung-Yi Ho
  • Publication number: 20240403629
    Abstract: Some embodiments of the present disclosure are directed to systems, computer-readable media, and computer-implemented methods for neural network calibration. Some embodiments are directed to determining a universal perturbation value and temperature scaling parameter based on a training data set, and processing a testing data set using a neural network by applying the universal perturbation value to the testing data set, and applying the temperature scaling parameter to a plurality of logits determined by the neural network based on the testing data set. Other embodiments may be disclosed or claimed.
    Type: Application
    Filed: June 2, 2023
    Publication date: December 5, 2024
    Inventors: Pin-Yu Chen, I-Hsin Chung, Bo Wu, Chuang Gan, Tsung-Yi Ho, Yung-Chen Tang
  • Patent number: 12061991
    Abstract: Transfer learning in machine learning can include receiving a machine learning model. Target domain training data for reprogramming the machine learning model using transfer learning can be received. The target domain training data can be transformed by performing a transformation function on the target domain training data. Output labels of the machine learning model can be mapped to target labels associated with the target domain training data. The transformation function can be trained by optimizing a parameter of the transformation function. The machine learning model can be reprogrammed based on input data transformed by the transformation function and a mapping of the output labels to target labels.
    Type: Grant
    Filed: September 23, 2020
    Date of Patent: August 13, 2024
    Assignees: International Business Machines Corporation, National Tsing Hua University
    Inventors: Pin-Yu Chen, Sijia Liu, Chia-Yu Chen, I-Hsin Chung, Tsung-Yi Ho, Yun-Yun Tsai
  • Publication number: 20220092407
    Abstract: Transfer learning in machine learning can include receiving a machine learning model. Target domain training data for reprogramming the machine learning model using transfer learning can be received. The target domain training data can be transformed by performing a transformation function on the target domain training data. Output labels of the machine learning model can be mapped to target labels associated with the target domain training data. The transformation function can be trained by optimizing a parameter of the transformation function. The machine learning model can be reprogrammed based on input data transformed by the transformation function and a mapping of the output labels to target labels.
    Type: Application
    Filed: September 23, 2020
    Publication date: March 24, 2022
    Inventors: Pin-Yu Chen, Sijia Liu, Chia-Yu Chen, I-Hsin Chung, Tsung-Yi Ho, Yun-Yun Tsai
  • Patent number: 11010528
    Abstract: A computer-implemented method for generating a layout of a design includes invoking the computer to receive a schematic representation of the design, generating a connection graph associated with the design, comparing the connection graph with a plurality of connection graphs stored in a database and selecting a layout associated with the matching connection graph in generating the layout of the design.
    Type: Grant
    Filed: January 12, 2016
    Date of Patent: May 18, 2021
    Assignee: SYNOPSYS, INC.
    Inventors: Tung-Chieh Chen, Po-Hsun Wu, Po-Hung Lin, Tsung-Yi Ho
  • Publication number: 20170124245
    Abstract: A computer-implemented method for generating a layout of a design includes invoking the computer to receive a schematic representation of the design, generating a connection graph associated with the design, comparing the connection graph with a plurality of connection graphs stored in a database and selecting a layout associated with the matching connection graph in generating the layout of the design.
    Type: Application
    Filed: January 12, 2016
    Publication date: May 4, 2017
    Inventors: Tung-Chieh Chen, Po-Hsun Wu, Po-Hung Lin, Tsung-Yi Ho
  • Patent number: 9256706
    Abstract: A computer-implemented method for generating a layout of a design includes invoking the computer to receive a schematic representation of the design, generating a connection graph associated with the design, comparing the connection graph with a plurality of connection graphs stored in a database and selecting a layout associated with the matching connection graph in generating the layout of the design.
    Type: Grant
    Filed: September 3, 2014
    Date of Patent: February 9, 2016
    Assignee: Synopsys Taiwan Co., Ltd.
    Inventors: Tung-Chieh Chen, Po-Hsun Wu, Po-Hung Lin, Tsung-Yi Ho
  • Publication number: 20150067626
    Abstract: A computer-implemented method for generating a layout of a design includes invoking the computer to receive a schematic representation of the design, generating a connection graph associated with the design, comparing the connection graph with a plurality of connection graphs stored in a database and selecting a layout associated with the matching connection graph in generating the layout of the design.
    Type: Application
    Filed: September 3, 2014
    Publication date: March 5, 2015
    Inventors: Tung-Chieh CHEN, Po-Hsun WU, Po-Hung LIN, Tsung-Yi HO
  • Patent number: 8751987
    Abstract: A method of resistor matching in analog integrated circuit layout is disclosed. Shapes of mismatching resistor blocks are analyzed to obtain geometrical information for deforming the mismatching resistor blocks. The mismatching resistor blocks are deformed into centrosymmetrical blocks according to the obtained geometrical information, each mismatching resistor block being decomposed to a plurality of unit-resistors. The unit-resistors are placed into matching resistor blocks to return a resulting layout with improved matching quality by reducing centroid offset between a centroid of the unit-resistors and a centroid of the matching resistor block.
    Type: Grant
    Filed: July 12, 2012
    Date of Patent: June 10, 2014
    Assignee: Oryx Holdings Pty Ltd.
    Inventors: Tsung-Yi Ho, Sheng-Jhih Jiang, Chan-Liang Wu
  • Patent number: 8726214
    Abstract: A floorplanning method for an analog integrated circuit layout is disclosed. A first-type block is defined as a movable and deformable block with rectangle constraint, and a second-type block is defined as a fixed-size block without rectangle constraint. Each block in the floorplan is classified to the first-type or the second-type block. In a shape determination stage, a target shape is determined among candidates of the first-type block, the first-type block accordingly being modified to the target shape, resulting in at least one overlap in the floorplan. In an overlap elimination stage, neighboring blocks of each said overlap are analyzed, the overlap being then eliminated by utilizing surrounding space, resulting in unused space in the floorplan. In an enlargement stage, the unused space is utilized for enlarging the first-type block.
    Type: Grant
    Filed: July 2, 2012
    Date of Patent: May 13, 2014
    Assignees: NCKU Research and Development Foundation, Himax Technologies, Ltd.
    Inventors: Tsung-Yi Ho, Sheng-Jhih Jiang, Chan-Liang Wu
  • Publication number: 20130283226
    Abstract: A floorplanning method for an analog integrated circuit layout is disclosed. A first-type block is defined as a movable and deformable block with rectangle constraint, and a second-type block is defined as a fixed-size block without rectangle constraint. Each block in the floorplan is classified to the first-type or the second-type block. In a shape determination stage, a target shape is determined among candidates of the first-type block, the first-type block accordingly being modified to the target shape, resulting in at least one overlap in the floorplan. In an overlap elimination stage, neighboring blocks of each said overlap are analyzed, the overlap being then eliminated by utilizing surrounding space, resulting in unused space in the floorplan. In an enlargement stage, the unused space is utilized for enlarging the first-type block.
    Type: Application
    Filed: July 2, 2012
    Publication date: October 24, 2013
    Applicants: HIMAX TECHNOLOGIES LIMITED, NCKU RESEARCH AND DEVELOPMENT FOUNDATION
    Inventors: Tsung-Yi Ho, Sheng-Jhih Jiang, Chan-Liang Wu
  • Publication number: 20130145332
    Abstract: A method of resistor matching in analog integrated circuit layout is disclosed. Shapes of mismatching resistor blocks are analyzed to obtain geometrical information for deforming the mismatching resistor blocks. The mismatching resistor blocks are deformed into centrosymmetrical blocks according to the obtained geometrical information, each mismatching resistor block being decomposed to a plurality of unit-resistors. The unit-resistors are placed into matching resistor blocks to return a resulting layout with improved matching quality by reducing centroid offset between a centroid of the unit-resistors and a centroid of the matching resistor block.
    Type: Application
    Filed: July 12, 2012
    Publication date: June 6, 2013
    Applicants: HIMAX TECHNOLOGIES LIMITED, NCKU RESEARCH AND DEVELOPMENT FOUNDATION
    Inventors: Tsung-Yi Ho, Sheng-Jhih Jiang, Chan-Liang Wu