Patents by Inventor Utku Aydonat

Utku Aydonat 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).

  • Patent number: 10726328
    Abstract: A method for implementing a convolutional neural network (CNN) accelerator on a target includes identifying characteristics and parameters for the CNN accelerator. Resources on the target are identified. A design for the CNN accelerator is generated in response to the characteristics and parameters of the CNN accelerator and the resources on the target.
    Type: Grant
    Filed: October 9, 2015
    Date of Patent: July 28, 2020
    Assignee: Altera Corporation
    Inventors: Andrew Chaang Ling, Gordon Raymond Chiu, Utku Aydonat
  • Publication number: 20200193267
    Abstract: A method for implementing a convolutional neural network (CNN) accelerator on a target includes utilizing one or more processing elements to implement a standard convolution layer. A configuration of the CNN accelerator is modified to change a data flow between components on the CNN accelerator. The one or more processing elements is utilized to implement a fully connected layer in response to the change in the data flow.
    Type: Application
    Filed: February 27, 2020
    Publication date: June 18, 2020
    Inventors: Utku Aydonat, Gordon Raymond Chiu, Andrew Chaang Ling
  • Patent number: 10614354
    Abstract: A method for implementing a convolutional neural network (CNN) accelerator on a target includes utilizing one or more processing elements to implement a standard convolution layer. A configuration of the CNN accelerator is modified to change a data flow between components on the CNN accelerator. The one or more processing elements is utilized to implement a fully connected layer in response to the change in the data flow.
    Type: Grant
    Filed: February 6, 2016
    Date of Patent: April 7, 2020
    Assignee: Altera Corporation
    Inventors: Utku Aydonat, Gordon Raymond Chiu, Andrew Chaang Ling
  • Patent number: 10083007
    Abstract: Devices and methods for filtering data include calculating intermediate input values from input elements using a transformation function. The transformation function is based at least in part on a size of the filter and a number of filter outputs. Intermediate filter values are calculated from filter elements of the filter using the transformation function. Each intermediate input value is multiplied with a respective intermediate filter value to form intermediate values. These intermediate values are combined with each other using the transformation function to determine one or more output values.
    Type: Grant
    Filed: September 15, 2016
    Date of Patent: September 25, 2018
    Assignee: ALTERA CORPORATION
    Inventors: Utku Aydonat, Andrew Chaang Ling, Gordon Raymond Chiu, Shane O'Connell
  • Publication number: 20180074787
    Abstract: Devices and methods for filtering data include calculating intermediate input values from input elements using a transformation function. The transformation function is based at least in part on a size of the filter and a number of filter outputs. Intermediate filter values are calculated from filter elements of the filter using the transformation function. Each intermediate input value is multiplied with a respective intermediate filter value to form intermediate values. These intermediate values are combined with each other using the transformation function to determine one or more output values.
    Type: Application
    Filed: September 15, 2016
    Publication date: March 15, 2018
    Inventors: Utku Aydonat, Andrew Chaang Ling, Gordon Raymond Chiu, Shane O'Connell
  • Publication number: 20170103298
    Abstract: A method for implementing a convolutional neural network (CNN) accelerator on a target includes identifying characteristics and parameters for the CNN accelerator. Resources on the target are identified. A design for the CNN accelerator is generated in response to the characteristics and parameters of the CNN accelerator and the resources on the target.
    Type: Application
    Filed: October 9, 2015
    Publication date: April 13, 2017
    Inventors: Andrew Chaang Ling, Gordon Raymond Chiu, Utku Aydonat
  • Publication number: 20170103299
    Abstract: A method for implementing a convolutional neural network (CNN) accelerator on a target includes utilizing one or more processing elements to implement a standard convolution layer. A configuration of the CNN accelerator is modified to change a data flow between components on the CNN accelerator. The one or more processing elements is utilized to implement a fully connected layer in response to the change in the data flow.
    Type: Application
    Filed: February 6, 2016
    Publication date: April 13, 2017
    Inventors: Utku Aydonat, Gordon Raymond Chiu, Andrew Chaang Ling