Patents by Inventor Sebastian Nowozin

Sebastian Nowozin 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: 20200394024
    Abstract: A computer program predictor is described which has a processor configured to access a program attribute predictor; and a memory storing a search component configured to search a space of possible programs, to find a program which, given an input data instance and an output data instance, will compute the output data instance from the input data instance, the search being guided by attributes predicted by the attribute predictor given the input data instance and the output data instance.
    Type: Application
    Filed: August 28, 2020
    Publication date: December 17, 2020
    Inventors: Alexander Lloyd GAUNT, Sebastian NOWOZIN, Marc Manuel Johannes BROCKSCHMIDT, Daniel Stefan TARLOW, Matej BALOG
  • Publication number: 20200380245
    Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.
    Type: Application
    Filed: March 10, 2020
    Publication date: December 3, 2020
    Inventors: Sebastian NOWOZIN, Tom ELLIS, Cecily Peregrine Borgatti MORRISON, Daniel COELHO DE CASTRO
  • Patent number: 10782939
    Abstract: A computer program predictor is described which has a processor configured to access a program attribute predictor; and a memory storing a search component configured to search a space of possible programs, to find a program which, given an input data instance and an output data instance, will compute the output data instance from the input data instance, the search being guided by attributes predicted by the attribute predictor given the input data instance and the output data instance.
    Type: Grant
    Filed: August 7, 2017
    Date of Patent: September 22, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Alexander Lloyd Gaunt, Sebastian Nowozin, Marc Manuel Johannes Brockschmidt, Daniel Stefan Tarlow, Matej Balog
  • Patent number: 10742990
    Abstract: A data compression apparatus is described which has an encoder configured to receive an input data item and to compress the data item into an encoding comprising a plurality of numerical values. The numerical values are grouped at least according to whether they relate to content of the input data item or style of the input data item. The encoder has been trained using a plurality of groups of training data items grouped according to the content and where training data items within individual ones of the groups vary with respect to the style. The encoder has been trained using a training objective which takes into account the groups.
    Type: Grant
    Filed: September 20, 2018
    Date of Patent: August 11, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sebastian Nowozin, Ryota Tomioka, Diane Bouchacourt
  • Publication number: 20200175022
    Abstract: In various examples there is a data retrieval apparatus. The apparatus has a processor configured to receive a data retrieval request associated with a user. The apparatus also has a machine learning system configured to compute an affinity matrix of users for data items. The affinity matrix has a plurality of observed ratings of data items, and a plurality of predicted ratings of data items. The processor is configured to output a ranked list of data items for the user according to contents of the affinity matrix.
    Type: Application
    Filed: March 18, 2019
    Publication date: June 4, 2020
    Inventors: Sebastian NOWOZIN, Cheng ZHANG, Noam KOENIGSTEIN, Chao MA, Jose Miguel Hernandez LOBATO, Wenbo GONG
  • Patent number: 10621416
    Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.
    Type: Grant
    Filed: October 2, 2017
    Date of Patent: April 14, 2020
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sebastian Nowozin, Tom Ellis, Cecily Peregrine Borgatti Morrison, Daniel Coelho De Castro
  • Publication number: 20190392587
    Abstract: A system to predict a location of a feature point of an articulated object from a plurality of data points relating to the articulated object of which some possess and some are missing 2D location data. The data points are input into a machine learning model that is trained to predict 2D location data for each feature point of the articulated object that was missing location data.
    Type: Application
    Filed: August 9, 2018
    Publication date: December 26, 2019
    Inventors: Sebastian NOWOZIN, Federica BOGO, Jamie Daniel Joseph SHOTTON, Jan STUEHMER
  • Publication number: 20190297328
    Abstract: A data compression apparatus is described which has an encoder configured to receive an input data item and to compress the data item into an encoding comprising a plurality of numerical values. The numerical values are grouped at least according to whether they relate to content of the input data item or style of the input data item. The encoder has been trained using a plurality of groups of training data items grouped according to the content and where training data items within individual ones of the groups vary with respect to the style. The encoder has been trained using a training objective which takes into account the groups.
    Type: Application
    Filed: September 20, 2018
    Publication date: September 26, 2019
    Inventors: Sebastian NOWOZIN, Ryota TOMIOKA, Diane BOUCHACOURT
  • Patent number: 10311378
    Abstract: A depth detection apparatus is described which has a memory storing raw time-of-flight sensor data received from a time-of-flight sensor. The depth detection apparatus also has a trained machine learning component having been trained using training data pairs. A training data pair comprises at least one simulated raw time-of-flight sensor data value and a corresponding simulated ground truth depth value. The trained machine learning component is configured to compute in a single stage, for an item of the stored raw time-of-flight sensor data, a depth value of a surface depicted by the item, by pushing the item through the trained machine learning component.
    Type: Grant
    Filed: August 8, 2017
    Date of Patent: June 4, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sebastian Nowozin, Amit Adam, Shai Mazor, Omer Yair
  • Publication number: 20190102606
    Abstract: An image processing system is described which has a memory holding at least one image depicting at least one person previously unseen by the image processing system. The system has a trained probabilistic model which describes a relationship between image features, context, identities and a plurality of names of people, wherein at least one of the identities identifies a person depicted in the image without an associated name in the plurality of names. The system has a feature extractor which extracts features from the image, and a processor which predicts an identity of the person depicted in the image using the extracted features and the probabilistic model.
    Type: Application
    Filed: October 2, 2017
    Publication date: April 4, 2019
    Inventors: Sebastian NOWOZIN, Tom ELLIS, Cecily Peregrine Borgatti MORRISON, Daniel COELHO DE CASTRO
  • Patent number: 10229502
    Abstract: A depth detection apparatus is described which has a memory and a computation logic. The memory stores frames of raw time-of-flight sensor data received from a time-of-flight sensor, the frames having been captured by a time-of-flight camera in the presence of motion such that different ones of the frames were captured using different locations of the camera and/or with different locations of an object in a scene depicted in the frames. The computation logic has functionality to compute a plurality of depth maps from the stream of frames, whereby each frame of raw time-of-flight sensor data contributes to more than one depth map.
    Type: Grant
    Filed: February 3, 2016
    Date of Patent: March 12, 2019
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Amit Adam, Sebastian Nowozin, Omer Yair, Shai Mazor, Michael Schober
  • Publication number: 20190042210
    Abstract: A computer program predictor is described which has a processor configured to access a program attribute predictor; and a memory storing a search component configured to search a space of possible programs, to find a program which, given an input data instance and an output data instance, will compute the output data instance from the input data instance, the search being guided by attributes predicted by the attribute predictor given the input data instance and the output data instance.
    Type: Application
    Filed: August 7, 2017
    Publication date: February 7, 2019
    Inventors: Alexander Lloyd GAUNT, Sebastian NOWOZIN, Marc Manuel Johannes BROCKSCHMIDT, Daniel Stefan TARLOW, Matej BALOG
  • Patent number: 10158859
    Abstract: A data compression apparatus is described which has an encoder configured to receive an input data item and to compress the data item into an encoding comprising a plurality of numerical values. The numerical values are grouped at least according to whether they relate to content of the input data item or style of the input data item. The encoder has been trained using a plurality of groups of training data items grouped according to the content and where training data items within individual ones of the groups vary with respect to the style. The encoder has been trained using a training objective which takes into account the groups.
    Type: Grant
    Filed: June 29, 2017
    Date of Patent: December 18, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sebastian Nowozin, Ryota Tomioka, Diane Bouchacourt
  • Publication number: 20180338147
    Abstract: A data compression apparatus is described which has an encoder configured to receive an input data item and to compress the data item into an encoding comprising a plurality of numerical values. The numerical values are grouped at least according to whether they relate to content of the input data item or style of the input data item. The encoder has been trained using a plurality of groups of training data items grouped according to the content and where training data items within individual ones of the groups vary with respect to the style. The encoder has been trained using a training objective which takes into account the groups.
    Type: Application
    Filed: June 29, 2017
    Publication date: November 22, 2018
    Inventors: Sebastian NOWOZIN, Ryota TOMIOKA, Diane BOUCHACOURT
  • Patent number: 10062201
    Abstract: Examples of time-of-flight (“TOF”) simulation of multipath light phenomena are described. For example, in addition to recording light intensity for a pixel during rendering, a graphics tool records the lengths (or times) and segment counts for light paths arriving at the pixel. Such multipath information can provide a characterization of the temporal light density of light that arrives at the pixel in response to one or more pulses of light. The graphics tool can use stratification and/or priority sampling to reduce variance in recorded light path samples. Realistic, physically-accurate simulation of multipath light phenomena can, in turn, help calibrate a TOF camera so that it more accurately estimates the depths of real world objects observed using the TOF camera. Various ways to improve the process of inferring imaging conditions such as depth, reflectivity, and ambient light based on images captured using a TOF camera are also described.
    Type: Grant
    Filed: April 21, 2015
    Date of Patent: August 28, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sebastian Nowozin, Amit Adam, Christoph Dann
  • Publication number: 20180129973
    Abstract: A depth detection apparatus is described which has a memory storing raw time-of-flight sensor data received from a time-of-flight sensor. The depth detection apparatus also has a trained machine learning component having been trained using training data pairs. A training data pair comprises at least one simulated raw time-of-flight sensor data value and a corresponding simulated ground truth depth value. The trained machine learning component is configured to compute in a single stage, for an item of the stored raw time-of-flight sensor data, a depth value of a surface depicted by the item, by pushing the item through the trained machine learning component.
    Type: Application
    Filed: August 8, 2017
    Publication date: May 10, 2018
    Inventors: Sebastian NOWOZIN, Amit ADAM, Shai MAZOR, Omer YAIR
  • Publication number: 20170372226
    Abstract: A multi-party privacy-preserving machine learning system is described which has a trusted execution environment comprising at least one protected memory region. An code loader at the system loads machine learning code, received from at least one of the parties, into the protected memory region. A data uploader uploads confidential data, received from at least one of the parties, to the protected memory region. The trusted execution environment executes the machine learning code using at least one data-oblivious procedure to process the confidential data and returns the result to at least one of the parties, where a data-oblivious procedure is a process where any patterns of memory accesses, patterns of disk accesses and patterns of network accesses are such that the confidential data cannot be predicted from the patterns.
    Type: Application
    Filed: August 23, 2016
    Publication date: December 28, 2017
    Inventors: Manuel Silverio da Silva Costa, Cédric Alain Marie Christophe Fournet, Aastha Mehta, Sebastian Nowozin, Olga Ohrimenko, Felix Schuster, Kapil Vaswani
  • Publication number: 20170262768
    Abstract: A depth detection apparatus is described which has a memory storing raw time-of-flight sensor data received from a time-of-flight sensor. The depth detection apparatus also has a trained machine learning component having been trained using training data pairs. A training data pair comprises at least one simulated raw time-of-flight sensor data value and a corresponding simulated ground truth depth value. The trained machine learning component is configured to compute in a single stage, for an item of the stored raw time-of-flight sensor data, a depth value of a surface depicted by the item, by pushing the item through the trained machine learning component.
    Type: Application
    Filed: March 13, 2016
    Publication date: September 14, 2017
    Inventors: Sebastian Nowozin, Amit Adam, Shai Mazor, Omer Yair
  • Patent number: 9760837
    Abstract: A depth detection apparatus is described which has a memory storing raw time-of-flight sensor data received from a time-of-flight sensor. The depth detection apparatus also has a trained machine learning component having been trained using training data pairs. A training data pair comprises at least one simulated raw time-of-flight sensor data value and a corresponding simulated ground truth depth value. The trained machine learning component is configured to compute in a single stage, for an item of the stored raw time-of-flight sensor data, a depth value of a surface depicted by the item, by pushing the item through the trained machine learning component.
    Type: Grant
    Filed: March 13, 2016
    Date of Patent: September 12, 2017
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Sebastian Nowozin, Amit Adam, Shai Mazor, Omer Yair
  • Publication number: 20170221212
    Abstract: A depth detection apparatus is described which has a memory and a computation logic. The memory stores frames of raw time-of-flight sensor data received from a time-of-flight sensor, the frames having been captured by a time-of-flight camera in the presence of motion such that different ones of the frames were captured using different locations of the camera and/or with different locations of an object in a scene depicted in the frames. The computation logic has functionality to compute a plurality of depth maps from the stream of frames, whereby each frame of raw time-of-flight sensor data contributes to more than one depth map.
    Type: Application
    Filed: February 3, 2016
    Publication date: August 3, 2017
    Inventors: Amit Adam, Sebastian Nowozin, Omer Yair, Shai Mazor, Michael Schober