Patents by Inventor Pushmeet Kohli
Pushmeet Kohli 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: 11983269Abstract: There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.Type: GrantFiled: December 22, 2022Date of Patent: May 14, 2024Assignee: DeepMind Technologies LimitedInventors: Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, Pushmeet Kohli
-
Publication number: 20240127045Abstract: A method performed by one or more computers for obtaining an optimized algorithm that (i) is functionally equivalent to a target algorithm and (ii) optimizes one or more target properties when executed on a target set of one or more hardware devices. The method includes: initializing a target tensor representing the target algorithm; generating, using a neural network having a plurality of network parameters, a tensor decomposition of the target tensor that parametrizes a candidate algorithm; generating target property values for each of the target properties when executing the candidate algorithm on the target set of hardware devices; determining a benchmarking score for the tensor decomposition based on the target property values of the candidate algorithm; generating a training example from the tensor decomposition and the benchmarking score; and storing, in a training data store, the training example for use in updating the network parameters of the neural network.Type: ApplicationFiled: October 3, 2022Publication date: April 18, 2024Inventors: Thomas Keisuke Hubert, Shih-Chieh Huang, Alexander Novikov, Alhussein Fawzi, Bernardino Romera-Paredes, David Silver, Demis Hassabis, Grzegorz Michal Swirszcz, Julian Schrittwieser, Pushmeet Kohli, Mohammadamin Barekatain, Matej Balog, Francisco Jesus Rodriguez Ruiz
-
Publication number: 20230134742Abstract: There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.Type: ApplicationFiled: December 22, 2022Publication date: May 4, 2023Inventors: Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, Pushmeet Kohli
-
Patent number: 11636347Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining a graph of nodes and edges that represents an interaction history of the agent with the environment; generating an encoded representation of the graph representing the interaction history of the agent with the environment; processing an input based on the encoded representation of the graph using an action selection neural network, in accordance with current values of action selection neural network parameters, to generate an action selection output; and selecting an action from a plurality of possible actions to be performed by the agent using the action selection output generated by the action selection neural network.Type: GrantFiled: January 22, 2020Date of Patent: April 25, 2023Assignee: DeepMind Technologies LimitedInventors: Hanjun Dai, Yujia Li, Chenglong Wang, Rishabh Singh, Po-Sen Huang, Pushmeet Kohli
-
Patent number: 11537719Abstract: There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.Type: GrantFiled: May 17, 2019Date of Patent: December 27, 2022Assignee: DeepMind Technologies LimitedInventors: Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, Pushmeet Kohli
-
Patent number: 11430123Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a plurality of possible segmentations of an image. In one aspect, a method comprises: receiving a request to generate a plurality of possible segmentations of an image; sampling a plurality of latent variables from a latent space, wherein each latent variable is sampled from the latent space in accordance with a respective probability distribution over the latent space that is determined based on the image; generating a plurality of possible segmentations of the image, comprising, for each latent variable, processing the image and the latent variable using a segmentation neural network having a plurality of segmentation neural network parameters to generate the possible segmentation of the image; and providing the plurality of possible segmentations of the image in response to the request.Type: GrantFiled: May 22, 2020Date of Patent: August 30, 2022Assignee: DeepMind Technologies LimitedInventors: Simon Kohl, Bernardino Romera-Paredes, Danilo Jimenez Rezende, Seyed Mohammadali Eslami, Pushmeet Kohli, Andrew Zisserman, Olaf Ronneberger
-
Patent number: 11120373Abstract: Crowdsourcing using active learning is described, for example, to select pairs of tasks and groups of workers so that information gained about answers to the tasks in the pool is optimized. In various examples a machine learning system learns variables describing characteristics of communities of workers, characteristics of workers, task variables and uncertainty of these variables. In various examples, the machine learning system predicts task variables and uncertainty of the predicted task variables for possible combinations of communities of workers and tasks. In examples the predicted variables and uncertainty are used to calculate expected information gain of the possible combinations and to rank the possible combinations. In examples, the crowdsourcing system uses the expected information gain to allocate tasks to worker communities and observe the results; the results may then be used to update the machine learning system.Type: GrantFiled: July 31, 2014Date of Patent: September 14, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Matteo Venanzi, John Philip Guiver, Pushmeet Kohli
-
Patent number: 11093702Abstract: Checking and/or completing for data grids is described such as for grids having rows and columns of cells at least some of which contain data values such as numbers or categories. In various embodiments predictive probability distributions are obtained from an inference engine for one or more of the cells and the predictive probability distributions are used for various tasks such as to suggest values to complete blank cells, highlight cells having outlying values, identify potential errors, suggest corrections to potential errors, identify similarities between cells, identify differences between cells, cluster rows of the data grid, and other tasks. In various embodiments a graphical user interface displays a data grid and provides facilities for completing, error checking/correcting, and analyzing data in the data grid.Type: GrantFiled: June 22, 2012Date of Patent: August 17, 2021Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: Thore Graepel, Filip Radlinski, Andrew Donald Gordon, Pushmeet Kohli, John Winn, Lucas Bordeaux, Yoram Bachrach
-
Publication number: 20200372654Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a plurality of possible segmentations of an image. In one aspect, a method comprises: receiving a request to generate a plurality of possible segmentations of an image; sampling a plurality of latent variables from a latent space, wherein each latent variable is sampled from the latent space in accordance with a respective probability distribution over the latent space that is determined based on the image; generating a plurality of possible segmentations of the image, comprising, for each latent variable, processing the image and the latent variable using a segmentation neural network having a plurality of segmentation neural network parameters to generate the possible segmentation of the image; and providing the plurality of possible segmentations of the image in response to the request.Type: ApplicationFiled: May 22, 2020Publication date: November 26, 2020Inventors: Simon Kohl, Bernardino Romera-Paredes, Danilo Jimenez Rezende, Seyed Mohammadali Eslami, Pushmeet Kohli, Andrew Zisserman, Olaf Ronneberger
-
Patent number: 10832163Abstract: Memory facilitation using directed acyclic graphs is described, for example, where a plurality of directed acyclic graphs are trained for gesture recognition from human skeletal data, or to estimate human body joint positions from depth images for gesture detection. In various examples directed acyclic graphs are grown during training using a training objective which takes into account both connection patterns between nodes and split function parameter values. For example, a layer of child nodes is grown and connected to a parent layer of nodes using an initialization strategy. In examples, various local search processes are used to find good combinations of connection patterns and split function parameters.Type: GrantFiled: October 28, 2016Date of Patent: November 10, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Jamie Daniel Joseph Shotton, Toby Sharp, Pushmeet Kohli, Reinhard Sebastian Bernhard Nowozin, John Michael Winn, Antonio Criminisi
-
Patent number: 10817552Abstract: Generally discussed herein are devices, systems, and methods for encoding input-output examples. A method of generating a program using an encoding of input-output examples, may include processing an input example of the input-output examples, using a first long short term memory (LSTM) neural network, one character at a time to produce an input feature vector, processing an output example associated with the input example in the input-output examples, using the LSTM neural network, one character at a time to produce an output feature vector, determining (a) a cross-correlation between the input feature vector and the output feature vector or (b) previously computed feature vectors for a different input-output example that are sufficiently close to the input feature vector and the output feature vector, respectively, and using the determined cross-correlation or previously computed vector, generating a program consistent with the input example and the output example.Type: GrantFiled: March 27, 2017Date of Patent: October 27, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Abdelrahman S. A. Mohamed, Pushmeet Kohli, Rishabh Singh, Emilio Parisotto
-
Patent number: 10795645Abstract: Described are systems, methods, and computer-readable media for program generation in a domain-specific language based on input-output examples. In accordance with various embodiments, a neural-network-based program generation model conditioned on an encoded set of input-output examples is used to generate a program tree by iteratively expanding a partial program tree, beginning with a root node and ending when all leaf nodes are terminal.Type: GrantFiled: March 27, 2017Date of Patent: October 6, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Abdelrahman S. A. Mohamed, Rishabh Singh, Lihong Li, Dengyong Zhou, Pushmeet Kohli, Emilio Parisotto
-
Patent number: 10762443Abstract: Crowdsourcing systems with machine learning are described. Specifically, item-label inference methods and systems are presented, for example, to provide aggregated answers to a crowdsourced task in a manner achieving good accuracy even where observed data about past behavior of crowd members is sparse. In various examples, an item-label inference system infers variables describing characteristics of both individual crowd workers and communities of the workers. In various examples, an item-label inference system provides aggregated labels while considering the inferred worker characteristics and the inferred characteristics of the worker communities. In examples the item-label inference system provides uncertainty information associated with the inference results for selecting workers and generating future tasks.Type: GrantFiled: July 17, 2017Date of Patent: September 1, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Matteo Venanzi, John Philip Guiver, Gabriella Kazai, Pushmeet Kohli, Milad Shokouhi
-
Patent number: 10761612Abstract: In one or more implementations, a static geometry model is generated, from one or more images of a physical environment captured using a camera, using one or more static objects to model corresponding one or more objects in the physical environment. Interaction of a dynamic object with at least one of the static objects is identified by analyzing at least one image and a gesture is recognized from the identified interaction of the dynamic object with the at least one of the static objects to initiate an operation of the computing device.Type: GrantFiled: May 15, 2019Date of Patent: September 1, 2020Assignee: Microsoft Technology Licensing, LLCInventors: David Kim, Otmar D. Hilliges, Shahram Izadi, Patrick L. Olivier, Jamie Daniel Joseph Shotton, Pushmeet Kohli, David G. Molyneaux, Stephen E. Hodges, Andrew W. Fitzgibbon
-
Publication number: 20200234145Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting actions to be performed by an agent interacting with an environment. In one aspect, a method comprises: obtaining a graph of nodes and edges that represents an interaction history of the agent with the environment; generating an encoded representation of the graph representing the interaction history of the agent with the environment; processing an input based on the encoded representation of the graph using an action selection neural network, in accordance with current values of action selection neural network parameters, to generate an action selection output; and selecting an action from a plurality of possible actions to be performed by the agent using the action selection output generated by the action selection neural network.Type: ApplicationFiled: January 22, 2020Publication date: July 23, 2020Inventors: Hanjun Dai, Yujia Li, Chenglong Wang, Rishabh Singh, Po-Sen Huang, Pushmeet Kohli
-
Publication number: 20190354689Abstract: There is described a neural network system implemented by one or more computers for determining graph similarity. The neural network system comprises one or more neural networks configured to process an input graph to generate a node state representation vector for each node of the input graph and an edge representation vector for each edge of the input graph; and process the node state representation vectors and the edge representation vectors to generate a vector representation of the input graph. The neural network system further comprises one or more processors configured to: receive a first graph; receive a second graph; generate a vector representation of the first graph; generate a vector representation of the second graph; determine a similarity score for the first graph and the second graph based upon the vector representations of the first graph and the second graph.Type: ApplicationFiled: May 17, 2019Publication date: November 21, 2019Inventors: Yujia Li, Chenjie Gu, Thomas Dullien, Oriol Vinyals, Pushmeet Kohli
-
Publication number: 20190278380Abstract: In one or more implementations, a static geometry model is generated, from one or more images of a physical environment captured using a camera, using one or more static objects to model corresponding one or more objects in the physical environment. Interaction of a dynamic object with at least one of the static objects is identified by analyzing at least one image and a gesture is recognized from the identified interaction of the dynamic object with the at least one of the static objects to initiate an operation of the computing device.Type: ApplicationFiled: May 15, 2019Publication date: September 12, 2019Applicant: Microsoft Technology Licensing, LLCInventors: David Kim, Otmar D. Hilliges, Shahram Izadi, Patrick L. Olivier, Jamie Daniel Joseph Shotton, Pushmeet Kohli, David G. Molyneaux, Stephen E. Hodges, Andrew W. Fitzgibbon
-
Patent number: 10346856Abstract: Personality aggregation and web browsing is described, for example, to find personality profiles of website audiences for use in recommendation systems, advertising systems, or other web services. In an embodiment natural browsing sequences of users who have given their consent are submitted to a pattern matching process to identify personality trait scores serendipitously occurring in the sequences. In an embodiment, an aggregator combines the personality trait scores by website to obtain audience personality profiles. In an example, a machine learning process carries out the aggregation and enables audience personality profiles of other websites to be predicted. For example, a random decision forest is trained using the natural browsing sequences having identified personality trait scores and once trained, is used to predict personality trait scores of other websites.Type: GrantFiled: August 9, 2012Date of Patent: July 9, 2019Assignee: Microsoft Technology Licensing, LLCInventors: Pushmeet Kohli, Filip Radlinski, Michael Stanislaw Kosinski
-
Patent number: 10331222Abstract: In one or more implementations, a static geometry model is generated, from one or more images of a physical environment captured using a camera, using one or more static objects to model corresponding one or more objects in the physical environment. Interaction of a dynamic object with at least one of the static objects is identified by analyzing at least one image and a gesture is recognized from the identified interaction of the dynamic object with the at least one of the static objects to initiate an operation of the computing device.Type: GrantFiled: May 24, 2016Date of Patent: June 25, 2019Assignee: MICROSOFT TECHNOLOGY LICENSING, LLCInventors: David Kim, Otmar D. Hilliges, Shahram Izadi, Patrick L. Olivier, Jamie Daniel Joseph Shotton, Pushmeet Kohli, David G. Molyneaux, Stephen E. Hodges, Andrew W. Fitzgibbon
-
Patent number: 10311282Abstract: Region of interest detection in raw time of flight images is described. For example, a computing device receives at least one raw image captured for a single frame by a time of flight camera. The raw image depicts one or more objects in an environment of the time of flight camera (such as human hands, bodies or any other objects). The raw image is input to a trained region detector and in response one or more regions of interest in the raw image are received. A received region of interest comprises image elements of the raw image which are predicted to depict at least part of one of the objects. A depth computation logic computes depth from the one or more regions of interest of the raw image.Type: GrantFiled: September 11, 2017Date of Patent: June 4, 2019Assignee: Microsoft Technology Licensing, LLCInventors: Jamie Daniel Joseph Shotton, Cem Keskin, Christoph Rhemann, Toby Sharp, Duncan Paul Robertson, Pushmeet Kohli, Andrew William Fitzgibbon, Shahram Izadi