Patents by Inventor Bodo RUCKAUER

Bodo RUCKAUER 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).

  • Neural network apparatus and method
    Patent number: 11853875
    Abstract: A processor-implemented neural network method includes acquiring connection weight of an analog neural network (ANN) node of a pre-trained ANN; and determining, a firing rate of a spiking neural network (SNN) node of an SNN, corresponding to the ANN node, based on an activation of the ANN node which is determined based on the connection weight. and the firing rate is also determined based on information indicating a timing at which the SNN node initially fires.
    Type: Grant
    Filed: October 23, 2018
    Date of Patent: December 26, 2023
    Assignees: Samsung Electronics Co., Ltd., UNIVERSITAET ZUERICH
    Inventors: Bodo Ruckauer, Shih-Chii Liu
  • Method of converting neural network and recognition apparatus using the same
    Patent number: 10977550
    Abstract: A neural network conversion method and a recognition apparatus that implements the method are provided. A method of converting an analog neural network (ANN) to a spiking neural network (SNN) normalizes first parameters of a trained ANN based on a reference activation that is set to be proximate to a maximum activation of artificial neurons included in the ANN, and determines second parameters of an SNN based on the normalized first parameters.
    Type: Grant
    Filed: June 23, 2017
    Date of Patent: April 13, 2021
    Assignees: SAMSUNG ELECTRONICS CO., LTD., UNIVERSITAET ZUERICH
    Inventors: Bodo Ruckauer, Iulia-Alexandra Lungu, Yuhuang Hu, Michael Pfeiffer
  • NEURAL NETWORK APPARATUS AND METHOD
    Publication number: 20190122110
    Abstract: A processor-implemented neural network method includes acquiring connection weight of an analog neural network (ANN) node of a pre-trained ANN; and determining, a firing rate of a spiking neural network (SNN) node of an SNN, corresponding to the ANN node, based on an activation of the ANN node which is determined based on the connection weight. and the firing rate is also determined based on information indicating a timing at which the SNN node initially fires.
    Type: Application
    Filed: October 23, 2018
    Publication date: April 25, 2019
    Applicants: SAMSUNG ELECTRONICS CO., LTD., UNIVERSITAET ZUERICH
    Inventors: Bodo RUCKAUER, Shih-Chii LIU
  • METHOD OF CONVERTING NEURAL NETWORK AND RECOGNITION APPARATUS USING THE SAME
    Publication number: 20180121802
    Abstract: A neural network conversion method and a recognition apparatus that implements the method are provided. A method of converting an analog neural network (ANN) to a spiking neural network (SNN) normalizes first parameters of a trained ANN based on a reference activation that is set to be proximate to a maximum activation of artificial neurons included in the ANN, and determines second parameters of an SNN based on the normalized first parameters.
    Type: Application
    Filed: June 23, 2017
    Publication date: May 3, 2018
    Applicants: SAMSUNG ELECTRONICS CO., LTD., UNIVERSITAET ZUERICH
    Inventors: Bodo RUCKAUER, Iulia-Alexandra LUNGU, Yuhuang HU, Michael PFEIFFER