Patents by Inventor Nicolas Le Roux

Nicolas Le Roux 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: 8239336
    Abstract: Data processing using restricted Boltzmann machines is described, for example, to pre-process continuous data and provide binary outputs. In embodiments, restricted Boltzmann machines based on either Gaussian distributions or Beta distributions are described which are able to learn and model both the mean and variance of data. In some embodiments, a stack of restricted Boltzmann machines are connected in series with outputs of one restricted Boltzmann machine providing input to the next in the stack and so on. Embodiments describe how training for each machine in the stack may be carried out efficiently and the combined system used for one of a variety of applications such as data compression, object recognition, image processing, information retrieval, data analysis and the like.
    Type: Grant
    Filed: March 9, 2009
    Date of Patent: August 7, 2012
    Assignee: Microsoft Corporation
    Inventors: Nicolas Le Roux, John Winn, Jamie Daniel Joseph Shotton
  • Patent number: 8229221
    Abstract: Image processing using masked restricted Boltzmann machines is described. In an embodiment restricted Boltzmann machines based on beta distributions are described which are implemented in an image processing system. In an embodiment a plurality of fields of masked RBMs are connected in series. An image is input into a masked appearance RBM and decomposed into superpixel elements. The superpixel elements output from one appearance RBM are used as input to a further appearance RBM. The outputs from each of the series of fields of RBMs are used in an intelligent image processing system. Embodiments describe training a plurality of RBMs. Embodiments describe using the image processing system for applications such as object recognition and image editing.
    Type: Grant
    Filed: August 4, 2009
    Date of Patent: July 24, 2012
    Assignee: Microsoft Corporation
    Inventors: Nicolas Le Roux, John Winn, Jamie Daniel Joseph Shotton, Nicolas Manfred Otto Heess
  • Publication number: 20110033122
    Abstract: Image processing using masked restricted Boltzmann machines is described. In an embodiment restricted Boltzmann machines based on beta distributions are described which are implemented in an image processing system. In an embodiment a plurality of fields of masked RBMs are connected in series. An image is input into a masked appearance RBM and decomposed into superpixel elements. The superpixel elements output from one appearance RBM are used as input to a further appearance RBM. The outputs from each of the series of fields of RBMs are used in an intelligent image processing system. Embodiments describe training a plurality of RBMs. Embodiments describe using the image processing system for applications such as object recognition and image editing.
    Type: Application
    Filed: August 4, 2009
    Publication date: February 10, 2011
    Applicant: Microsoft Corporation
    Inventors: Nicolas Le Roux, John Winn, Jamie Daniel Joseph Shotton, Nicolas Manfred Otto Heess
  • Publication number: 20100228694
    Abstract: Data processing using restricted Boltzmann machines is described, for example, to pre-process continuous data and provide binary outputs. In embodiments, restricted Boltzmann machines based on either Gaussian distributions or Beta distributions are described which are able to learn and model both the mean and variance of data. In some embodiments, a stack of restricted Boltzmann machines are connected in series with outputs of one restricted Boltzmann machine providing input to the next in the stack and so on. Embodiments describe how training for each machine in the stack may be carried out efficiently and the combined system used for one of a variety of applications such as data compression, object recognition, image processing, information retrieval, data analysis and the like.
    Type: Application
    Filed: March 9, 2009
    Publication date: September 9, 2010
    Applicant: Microsoft Corporation
    Inventors: Nicolas Le Roux, John Winn, Jamie Daniel Joseph Shotton