Patents by Inventor Rajat Monga
Rajat Monga 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: 11803595Abstract: The present disclosure provides systems and methods for data analysis. An example method may comprise receiving a data stream comprising a plurality of records. A record of said plurality of records may comprise a plurality of attributes. The method may further comprise classifying each of said plurality of attributes as a dimension or a measure. The method may further comprise dividing said plurality of records into a plurality of time periods. The method may further comprise, for a time period of said plurality of time periods, generating one or more segments of records. Each segment of the one or more segments may comprise records having a combination of dimensions with unique values as compared to other segments of said one or more segments. The method may further comprise applying an algorithm to said one or more segments to generate an output. The method may further comprise displaying, on a graphical user interface, a graphical representation of said output to a user.Type: GrantFiled: February 14, 2022Date of Patent: October 31, 2023Assignee: INFERENCE IP, LLCInventors: Rajat Monga, Suharsh Sivakumar, Varun Saini
-
Patent number: 11687832Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.Type: GrantFiled: August 3, 2020Date of Patent: June 27, 2023Assignee: Google LLCInventors: Gregory S. Corrado, Kai Chen, Jeffrey A. Dean, Samy Bengio, Rajat Monga, Matthieu Devin
-
Patent number: 11074454Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying videos using neural networks. One of the methods includes obtaining a temporal sequence of video frames, wherein the temporal sequence comprises a respective video frame from a particular video at each of a plurality time steps; for each time step of the plurality of time steps: processing the video frame at the time step using a convolutional neural network to generate features of the video frame; and processing the features of the video frame using an LSTM neural network to generate a set of label scores for the time step and classifying the video as relating to one or more of the topics represented by labels in the set of labels from the label scores for each of the plurality of time steps.Type: GrantFiled: May 13, 2019Date of Patent: July 27, 2021Assignee: Google LLCInventors: Sudheendra Vijayanarasimhan, George Dan Toderici, Yue Hei Ng, Matthew John Hausknecht, Oriol Vinyals, Rajat Monga
-
Patent number: 10733535Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.Type: GrantFiled: July 31, 2017Date of Patent: August 4, 2020Assignee: Google LLCInventors: Gregory S. Corrado, Kai Chen, Jeffrey A. Dean, Samy Bengio, Rajat Monga, Matthieu Devin
-
Patent number: 10289912Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying videos using neural networks. One of the methods includes obtaining a temporal sequence of video frames, wherein the temporal sequence comprises a respective video frame from a particular video at each of a plurality time steps; for each time step of the plurality of time steps: processing the video frame at the time step using a convolutional neural network to generate features of the video frame; and processing the features of the video frame using an LSTM neural network to generate a set of label scores for the time step and classifying the video as relating to one or more of the topics represented by labels in the set of labels from the label scores for each of the plurality of time steps.Type: GrantFiled: April 29, 2016Date of Patent: May 14, 2019Assignee: Google LLCInventors: Sudheendra Vijayanarasimhan, George Dan Toderici, Yue Hei Ng, Matthew John Hausknecht, Oriol Vinyals, Rajat Monga
-
Patent number: 9721214Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.Type: GrantFiled: August 8, 2016Date of Patent: August 1, 2017Assignee: Google Inc.Inventors: Gregory S. Corrado, Kai Chen, Jeffrey A. Dean, Samy Bengio, Rajat Monga, Matthieu Devin
-
Patent number: 9412065Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.Type: GrantFiled: August 4, 2015Date of Patent: August 9, 2016Assignee: Google Inc.Inventors: Gregory S. Corrado, Kai Chen, Jeffrey A. Dean, Samy Bengio, Rajat Monga, Matthieu Devin
-
Patent number: 9355067Abstract: Systems and methods are disclosed for distributed first- or higher-order model fitting algorithms. Determination of the parameter set for the objective function is divided into a plurality of sub-processes, each performed by one of a plurality of worker computers. A master computer coordinates the operation of the plurality of worker computers, each operating on a portion of the parameter set such that no two worker computers contain exactly the same parameter subset nor the complete parameter set. Each worker computer performs its sub-processes on its parameter subset, together with training data. For maximum efficiency, the sub-processes are performed using a compact set of instruction primitives. The results are evaluated by the master computer, which may coordinate additional sub-process operations to perform higher-order optimization or terminate the optimization method and proceed to formulation of a model function.Type: GrantFiled: April 20, 2015Date of Patent: May 31, 2016Assignee: Google Inc.Inventors: Rajat Monga, Xiaoyun Wu, Andrew Yan-Tak Ng
-
Patent number: 9218573Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.Type: GrantFiled: March 14, 2013Date of Patent: December 22, 2015Assignee: Google Inc.Inventors: Gregory S. Corrado, Kai Chen, Jeffrey A. Dean, Samy Bengio, Rajat Monga, Matthieu Devin
-
Patent number: 9015083Abstract: Systems and methods are disclosed for distributed first- or higher-order model fitting algorithms. Determination of the parameter set for the objective function is divided into a plurality of sub-processes, each performed by one of a plurality of worker computers. A master computer coordinates the operation of the plurality of worker computers, each operating on a portion of the parameter set such that no two worker computers contain exactly the same parameter subset nor the complete parameter set. Each worker computer performs its sub-processes on its parameter subset, together with training data. For maximum efficiency, the sub-processes are performed using a compact set of instruction primitives. The results are evaluated by the master computer, which may coordinate additional sub-process operations to perform higher-order optimization or terminate the optimization method and proceed to formulation of a model function.Type: GrantFiled: March 23, 2012Date of Patent: April 21, 2015Assignee: Google Inc.Inventors: Rajat Monga, Xiaoyun Wu, Andrew Yan-Tak Ng
-
Patent number: 8768870Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.Type: GrantFiled: August 15, 2013Date of Patent: July 1, 2014Assignee: Google Inc.Inventors: Gregory S. Corrado, Kai Chen, Jeffrey A. Dean, Samy Bengio, Rajat Monga, Matthieu Devin
-
Publication number: 20100268628Abstract: Managing controlled content on a web page is disclosed. A web page is analyzed. Controlled content and revenue-generating code are detected on the web page. A party to contact is determined based on the revenue-generating code or the controlled content.Type: ApplicationFiled: April 15, 2009Publication date: October 21, 2010Inventors: James E. Pitkow, Dejan Diklic, Rajat Monga