Patents by Inventor Matthias Bethge

Matthias Bethge 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: 20220284288
    Abstract: The present disclosure relates to machine-learning generalization, and in particular to techniques for regularizing machine-learning The present disclosure relates to machine-learning generalization, and in particular to techniques for regularizing machine-learning models using biological systems (e.g. brain data) to engineer machine-learning-algorithms that can generalize better. Particularly, aspects are directed to a computer implemented method that includes measuring a plurality of biological responses (e.g. neural responses to stimuli or other variables such body movements); generating data (e.g. responses to stimuli) using the predictive model which can denoise biological data and extract task relevant information; scaling and transforming these predictions (e.g. measure representational similarities between stimuli); and using the biologically derived data to regularize machine-learning-algorithms.
    Type: Application
    Filed: September 24, 2020
    Publication date: September 8, 2022
    Applicants: BAYLOR COLLEGE OF MEDICINE, UNIVERSITY OF TUBINGEN
    Inventors: ANDREAS TOLIAS, ZHE LI, ZACHARY PITKOW, JOSUE ORTEGA CARO, ANKIT PATEL, JACOB REIMER, MATTHIAS BETHGE, FABIAN SINZ
  • Publication number: 20180158224
    Abstract: Computer-implemented method for transferring style features from at least one source image to a target image, comprising the steps of generating a result image, based on the source and the target image, wherein one or more spatially-variant features of the result image correspond to one or more spatially variant features of the target image; and wherein a texture of the result image corresponds to a texture of the source image; and outputting the result image, and a corresponding device. According to the invention, the texture corresponds to a summary statistic of spatially variant features of the source image.
    Type: Application
    Filed: January 26, 2018
    Publication date: June 7, 2018
    Inventors: Matthias BETHGE, Leon GATYS
  • Patent number: 8750603
    Abstract: A method for compressing a digital image includes selecting an image patch of the digital image; assigning the selected image patch to a specific class (z); transforming the image patch, with a pre-determined class-specific transformation function; and quantizing the transformed image patch, wherein parameters of the classifier have been learned from a set of training image patches.
    Type: Grant
    Filed: December 2, 2010
    Date of Patent: June 10, 2014
    Assignee: Max-Planck-Gesellschaft zur Förderung der Wissenschaften e.V.
    Inventors: Matthias Bethge, Reshad Hosseini
  • Publication number: 20110069755
    Abstract: A method for compressing a digital image includes selecting an image patch of the digital image; assigning the selected image patch to a specific class (z); transforming the image patch, with a pre-determined class-specific transformation function; and quantizing the transformed image patch, wherein parameters of the classifier have been learned from a set of training image patches.
    Type: Application
    Filed: December 2, 2010
    Publication date: March 24, 2011
    Applicant: Max-Planck-Gesellschaft zur Forderung der Wissenschaften e.V.
    Inventors: Matthias Bethge, Reshad Hosseini