Patents by Inventor Daniel Stefan Tarlow

Daniel Stefan Tarlow 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: 11972234
    Abstract: Systems and methods of the present disclosure are directed to a method for machine-learned code segment prediction for optimizing software development. The method includes obtaining an incomplete segment of code. The method includes processing the incomplete segment of code with a machine-learned code prediction model to obtain a sampled set of segment completion predictions that include code that completes the incomplete segment of code. The method includes determining an aggregated segment completion prediction from the sampled set of segment completion predictions. The method includes replacing a portion of the aggregated segment completion prediction with an input field, wherein the portion of the aggregated segment completion prediction is associated with a degree of certainty less than a threshold degree of certainty.
    Type: Grant
    Filed: June 3, 2022
    Date of Patent: April 30, 2024
    Assignee: GOOGLE LLC
    Inventors: Daniel Dun-Ning Woo Johnson, Daniel Stefan Tarlow, Maxim Tabachnyk, Marc Hatcher Rasi, Jacob Austin, Hassan Abolhassani, Jacob Hanson Hegna
  • Publication number: 20240036832
    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: October 9, 2023
    Publication date: February 1, 2024
    Inventors: Alexander Lloyd GAUNT, Sebastian NOWOZIN, Marc Manuel Johannes BROCKSCHMIDT, Daniel Stefan TARLOW, Matej BALOG
  • Publication number: 20230393817
    Abstract: Systems and methods of the present disclosure are directed to a method for machine-learned code segment prediction for optimizing software development. The method includes obtaining an incomplete segment of code. The method includes processing the incomplete segment of code with a machine-learned code prediction model to obtain a sampled set of segment completion predictions that include code that completes the incomplete segment of code. The method includes determining an aggregated segment completion prediction from the sampled set of segment completion predictions. The method includes replacing a portion of the aggregated segment completion prediction with an input field, wherein the portion of the aggregated segment completion prediction is associated with a degree of certainty less than a threshold degree of certainty.
    Type: Application
    Filed: June 3, 2022
    Publication date: December 7, 2023
    Inventors: Daniel Dun-ning Woo Johnson, Daniel Stefan Tarlow, Maxim Tabachnyk, Marc Hatcher Rasi, Jacob Austin, Hassan Abolhassani, Jacob Hanson Hegna
  • Patent number: 11816457
    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 28, 2020
    Date of Patent: November 14, 2023
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Alexander Lloyd Gaunt, Sebastian Nowozin, Marc Manuel Johannes Brockschmidt, Daniel Stefan Tarlow, Matej Balog
  • Publication number: 20220222531
    Abstract: A neural network training apparatus is described which has a network of worker nodes each having a memory storing a subgraph of a neural network to be trained. The apparatus has a control node connected to the network of worker nodes. The control node is configured to send training data instances into the network to trigger parallelized message passing operations which implement a training algorithm which trains the neural network. At least some of the message passing operations asynchronously update parameters of individual subgraphs of the neural network at the individual worker nodes.
    Type: Application
    Filed: March 28, 2022
    Publication date: July 14, 2022
    Inventors: Ryota TOMIOKA, Matthew Alastair JOHNSON, Daniel Stefan TARLOW, Samuel Alexander WEBSTER, Dimitrios VYTINIOTIS, Alexander Lloyd GAUNT, Maik RIECHERT
  • Patent number: 11288575
    Abstract: A neural network training apparatus is described which has a network of worker nodes each having a memory storing a subgraph of a neural network to be trained. The apparatus has a control node connected to the network of worker nodes. The control node is configured to send training data instances into the network to trigger parallelized message passing operations which implement a training algorithm which trains the neural network. At least some of the message passing operations asynchronously update parameters of individual subgraphs of the neural network at the individual worker nodes.
    Type: Grant
    Filed: May 18, 2017
    Date of Patent: March 29, 2022
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Ryota Tomioka, Matthew Alastair Johnson, Daniel Stefan Tarlow, Samuel Alexander Webster, Dimitrios Vytiniotis, Alexander Lloyd Gaunt, Maik Riechert
  • 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
  • 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
  • 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
  • Publication number: 20180336458
    Abstract: A neural network training apparatus is described which has a network of worker nodes each having a memory storing a subgraph of a neural network to be trained. The apparatus has a control node connected to the network of worker nodes. The control node is configured to send training data instances into the network to trigger parallelized message passing operations which implement a training algorithm which trains the neural network. At least some of the message passing operations asynchronously update parameters of individual subgraphs of the neural network at the individual worker nodes.
    Type: Application
    Filed: May 18, 2017
    Publication date: November 22, 2018
    Inventors: Ryota TOMIOKA, Matthew Alastair JOHNSON, Daniel Stefan TARLOW, Samuel Alexander WEBSTER, Dimitrios VYTINIOTIS, Alexander Lloyd GAUNT, Maik RIECHERT
  • Patent number: 10127497
    Abstract: An inference engine is described for efficient machine learning. For example, an inference engine executes a plurality of ordered steps to carry out inference on the basis of observed data. For each step, a plurality of inputs to the step are received. A predictor predicts an output of the step and computes uncertainty of the prediction. Either the predicted output or a known output is selected on the basis of the uncertainty. If the known output is selected, the known output is computed, (for example, using a resource intensive, accurate process). The predictor is retrained using the known output and the plurality of inputs of the step as training data. For example, computing the prediction is fast and efficient as compared with computing the known output.
    Type: Grant
    Filed: October 14, 2014
    Date of Patent: November 13, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Seyed Mohammadali Eslami, Daniel Stefan Tarlow, Pushmeet Kohli, John Winn
  • Patent number: 10037624
    Abstract: Examples describe an apparatus for calibrating a three dimensional (3D) mesh model of an articulated object. The articulated object is an instance of a specified object class. The apparatus comprises an input configured to receive captured sensor data depicting the object. The apparatus has a calibration engine configured to compute values of shape parameters of the 3D mesh model which indicate which member of the object class is depicted in the captured sensor data, in order to calibrate the 3D mesh model. The calibration engine is configured to compute the values of the shape parameters with an optimization process to find at least one potential local or global minimum of an energy function, the energy function expressing a degree of similarity between data rendered from the model and the received sensor data.
    Type: Grant
    Filed: December 29, 2015
    Date of Patent: July 31, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Thomas Joseph Cashman, David Joseph New Tan, Jamie Daniel Joseph Shotton, Andrew William Fitzgibbon, Sameh Khamis, Jonathan James Taylor, Toby Sharp, Daniel Stefan Tarlow
  • Patent number: 9928040
    Abstract: Automated generation, or completion, or checking of source code is described whereby a probabilistic model having been trained using a corpus of natural source code examples is used. In various examples the probabilistic model comprises probability distributions describing belief about structure of natural source code and takes into account source code analysis from a compiler or other source code analyzer. In various examples, source code analysis may comprise syntactic structure, type information and other data about source code. In various examples, the trained probabilistic model is used to predict sequences of source code elements. For example, to generate source code, to auto-complete source code, to error check source code, to error correct source code or for other purposes.
    Type: Grant
    Filed: February 26, 2014
    Date of Patent: March 27, 2018
    Assignee: Microsoft Technology Licensing, LLC
    Inventors: Daniel Stefan Tarlow, Christopher Joseph Maddison
  • Publication number: 20170186226
    Abstract: Examples describe an apparatus for calibrating a three dimensional (3D) mesh model of an articulated object. The articulated object is an instance of a specified object class. The apparatus comprises an input configured to receive captured sensor data depicting the object. The apparatus has a calibration engine configured to compute values of shape parameters of the 3D mesh model which indicate which member of the object class is depicted in the captured sensor data, in order to calibrate the 3D mesh model. The calibration engine is configured to compute the values of the shape parameters with an optimization process to find at least one potential local or global minimum of an energy function, the energy function expressing a degree of similarity between data rendered from the model and the received sensor data.
    Type: Application
    Filed: December 29, 2015
    Publication date: June 29, 2017
    Inventors: Thomas Joseph CASHMAN, David Joseph New TAN, Jamie Daniel Joseph SHOTTON, Andrew William FITZGIBBON, Sameh KHAMIS, Jonathan James TAYLOR, Toby SHARP, Daniel Stefan TARLOW
  • Publication number: 20160104070
    Abstract: An inference engine is described for efficient machine learning. For example, an inference engine executes a plurality of ordered steps to carry out inference on the basis of observed data. For each step, a plurality of inputs to the step are received. A predictor predicts an output of the step and computes uncertainty of the prediction. Either the predicted output or a known output is selected on the basis of the uncertainty. If the known output is selected, the known output is computed, (for example, using a resource intensive, accurate process). The predictor is retrained using the known output and the plurality of inputs of the step as training data. For example, computing the prediction is fast and efficient as compared with computing the known output.
    Type: Application
    Filed: October 14, 2014
    Publication date: April 14, 2016
    Inventors: Seyed Mohammadali Eslami, Daniel Stefan Tarlow, Pushmeet Kohli, John Winn
  • Publication number: 20150135166
    Abstract: Automated generation, or completion, or checking of source code is described whereby a probabilistic model having been trained using a corpus of natural source code examples is used. In various examples the probabilistic model comprises probability distributions describing belief about structure of natural source code and takes into account source code analysis from a compiler or other source code analyzer. In various examples, source code analysis may comprise syntactic structure, type information and other data about source code. In various examples, the trained probabilistic model is used to predict sequences of source code elements. For example, to generate source code, to auto-complete source code, to error check source code, to error correct source code or for other purposes.
    Type: Application
    Filed: February 26, 2014
    Publication date: May 14, 2015
    Applicant: Microsoft Corporation
    Inventors: Daniel Stefan Tarlow, Christopher Joseph Maddison