Patents by Inventor Vijay Vasudevan
Vijay Vasudevan 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: 11164363Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.Type: GrantFiled: July 8, 2020Date of Patent: November 2, 2021Assignee: Waymo LLCInventors: Yin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Yu Ouyang, Zijian Guo, Jiquan Ngiam, Vijay Vasudevan
-
Patent number: 11151446Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for receiving, by a computational graph system, a request to process a computational graph; obtaining data representing a subgraph of the computational graph, the computational graph comprising a plurality of nodes and directed edges, wherein each node represents a respective operation, wherein each directed edge connects a respective first node to a respective second node, the subgraph assigned to a first device by a placer in the computational graph system; determining that the first device comprises a hardware accelerator having a plurality of streams; in response to determining, generating instructions that when executed by the first device cause the first device to: assign the operation represented by each node in the subgraph to a respective stream; and perform the operations represented by the nodes in the subgraph in accordance with the assignment.Type: GrantFiled: October 27, 2016Date of Patent: October 19, 2021Assignee: Google LLCInventors: Paul Ronald Barham, Vijay Vasudevan
-
Publication number: 20210279465Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing data generated by a sensing system that rotationally senses an environment. In one aspect, a method comprises partitioning a predetermined period of time into a plurality of sub-periods, wherein the predetermined period of time is a period of time for which data generated by the sensing system constitutes a complete rotational sensing of the environment; for each sub-period: receiving current data generated by the sensing system during the sub-period and characterizing a respective partial scene of the environment; processing the current data using an object detection neural network to generate a current object detection output that is specific to the respective partial scene of the environment.Type: ApplicationFiled: March 6, 2020Publication date: September 9, 2021Inventors: Jonathon Shlens, Vijay Vasudevan, Jiquan Ngiam, Wei Han, Zhifeng Chen, Brandon Chauloon Yang, Benjamin James Caine, Zhengdong Zhang, Christoph Sprunk, Ouais Alsharif, Junhua Mao, Chen Wu
-
Publication number: 20210271970Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining update rules for training neural networks. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch defining a respective update rule; for each output sequence in the batch: training a respective instance of a child neural network using the update rule defined by the output sequence; evaluating a performance of the trained instance of the child neural network on the particular neural network task to determine a performance metric for the trained instance of the child neural network on the particular neural network task; and using the performance metrics for the trained instances of the child neural network to adjust the current values of the controller parameters of the controller neural network.Type: ApplicationFiled: January 11, 2021Publication date: September 2, 2021Inventors: Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc V. Le
-
Patent number: 11087216Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for modifying a computational graph to include send and receive nodes. Communication between unique devices performing operations of different subgraphs of the computational graph can be handled efficiently by inserting send and receive nodes into each subgraph. When executed, the operations that these send and receive nodes represent may enable pairs of unique devices to conduct communication with each other in a self-sufficient manner. This shifts the burden of coordinating communication away from the backend, which affords the system that processes this computational graph representation the opportunity to perform one or more other processes while devices are executing subgraphs.Type: GrantFiled: September 9, 2020Date of Patent: August 10, 2021Assignee: Google LLCInventors: Vijay Vasudevan, Jeffrey Adgate Dean, Sanjay Ghemawat
-
Patent number: 10922611Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining update rules for training neural networks. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch defining a respective update rule; for each output sequence in the batch: training a respective instance of a child neural network using the update rule defined by the output sequence; evaluating a performance of the trained instance of the child neural network on the particular neural network task to determine a performance metric for the trained instance of the child neural network on the particular neural network task; and using the performance metrics for the trained instances of the child neural network to adjust the current values of the controller parameters of the controller neural network.Type: GrantFiled: October 24, 2019Date of Patent: February 16, 2021Assignee: Google LLCInventors: Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc V. Le
-
Publication number: 20210019658Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.Type: ApplicationFiled: October 1, 2020Publication date: January 21, 2021Inventors: Vijay Vasudevan, Barret Zoph, Ekin Dogus Cubuk, Quoc V. Le
-
Publication number: 20210012555Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.Type: ApplicationFiled: July 8, 2020Publication date: January 14, 2021Inventors: Yin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Yu Ouyang, Zijian Guo, Jiquan Ngiam, Vijay Vasudevan
-
Publication number: 20210012089Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data representing a sensor measurement of a scene captured by one or more sensors to generate an object detection output that identifies locations of one or more objects in the scene. When deployed within an on-board system of a vehicle, the object detection output that is generated can be used to make autonomous driving decisions for the vehicle with enhanced accuracy.Type: ApplicationFiled: July 8, 2020Publication date: January 14, 2021Inventors: Jonathon Shlens, Patrick An Phu Nguyen, Benjamin James Caine, Jiquan Ngiam, Wei Han, Brandon Chauloon Yang, Yuning Chai, Pei Sun, Yin Zhou, Xi Yi, Ouais Alsharif, Zhifeng Chen, Vijay Vasudevan
-
Publication number: 20200401897Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for modifying a computational graph to include send and receive nodes. Communication between unique devices performing operations of different subgraphs of the computational graph can be handled efficiently by inserting send and receive nodes into each subgraph. When executed, the operations that these send and receive nodes represent may enable pairs of unique devices to conduct communication with each other in a self-sufficient manner. This shifts the burden of coordinating communication away from the backend, which affords the system that processes this computational graph representation the opportunity to perform one or more other processes while devices are executing subgraphs.Type: ApplicationFiled: September 9, 2020Publication date: December 24, 2020Inventors: Vijay Vasudevan, Jeffrey Adgate Dean, Sanjay Ghemawat
-
Patent number: 10817805Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.Type: GrantFiled: May 20, 2019Date of Patent: October 27, 2020Assignee: Google LLCInventors: Vijay Vasudevan, Barret Zoph, Ekin Dogus Cubuk, Quoc V. Le
-
Patent number: 10783435Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for modifying a computational graph to include send and receive nodes. Communication between unique devices performing operations of different subgraphs of the computational graph can be handled efficiently by inserting send and receive nodes into each subgraph. When executed, the operations that these send and receive nodes represent may enable pairs of unique devices to conduct communication with each other in a self-sufficient manner. This shifts the burden of coordinating communication away from the backend, which affords the system that processes this computational graph representation the opportunity to perform one or more other processes while devices are executing subgraphs.Type: GrantFiled: October 28, 2016Date of Patent: September 22, 2020Assignee: Google LLCInventors: Vijay Vasudevan, Jeffrey Adgate Dean, Sanjay Ghemawat
-
Publication number: 20200143227Abstract: The present disclosure is directed to an automated neural architecture search approach for designing new neural network architectures such as, for example, resource-constrained mobile CNN models. In particular, the present disclosure provides systems and methods to perform neural architecture search using a novel factorized hierarchical search space that permits layer diversity throughout the network, thereby striking the right balance between flexibility and search space size. The resulting neural architectures are able to be run relatively faster and using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art mobile-optimized models.Type: ApplicationFiled: January 28, 2019Publication date: May 7, 2020Inventors: Mingxing Tan, Quoc Le, Bo Chen, Vijay Vasudevan, Ruoming Pang
-
Publication number: 20200104710Abstract: A method for training a target neural network on a target machine learning task is described.Type: ApplicationFiled: September 27, 2019Publication date: April 2, 2020Inventors: Vijay Vasudevan, Ruoming Pang, Quoc V. Le, Daiyi Peng, Jiquan Ngiam, Simon Kornblith
-
Publication number: 20200065689Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network having controller parameters and in accordance with current values of the controller parameters, a batch of output sequences. The method includes, for each output sequence in the batch: generating an instance of a child convolutional neural network (CNN) that includes multiple instances of a first convolutional cell having an architecture defined by the output sequence; training the instance of the child CNN to perform an image processing task; and evaluating a performance of the trained instance of the child CNN on the task to determine a performance metric for the trained instance of the child CNN; and using the performance metrics for the trained instances of the child CNN to adjust current values of the controller parameters of the controller neural network.Type: ApplicationFiled: November 5, 2019Publication date: February 27, 2020Inventors: Vijay Vasudevan, Barret Zoph, Jonathon Shlens, Quoc V. Le
-
Publication number: 20200057941Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining update rules for training neural networks. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch defining a respective update rule; for each output sequence in the batch: training a respective instance of a child neural network using the update rule defined by the output sequence; evaluating a performance of the trained instance of the child neural network on the particular neural network task to determine a performance metric for the trained instance of the child neural network on the particular neural network task; and using the performance metrics for the trained instances of the child neural network to adjust the current values of the controller parameters of the controller neural network.Type: ApplicationFiled: October 24, 2019Publication date: February 20, 2020Inventors: Irwan Bello, Barret Zoph, Vijay Vasudevan, Quoc V. Le
-
Patent number: 10521729Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network having controller parameters and in accordance with current values of the controller parameters, a batch of output sequences. The method includes, for each output sequence in the batch: generating an instance of a child convolutional neural network (CNN) that includes multiple instances of a first convolutional cell having an architecture defined by the output sequence; training the instance of the child CNN to perform an image processing task; and evaluating a performance of the trained instance of the child CNN on the task to determine a performance metric for the trained instance of the child CNN; and using the performance metrics for the trained instances of the child CNN to adjust current values of the controller parameters of the controller neural network.Type: GrantFiled: July 19, 2018Date of Patent: December 31, 2019Assignee: Google LLCInventors: Vijay Vasudevan, Barret Zoph, Jonathon Shlens, Quoc V. Le
-
Publication number: 20190354895Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for learning a data augmentation policy for training a machine learning model. In one aspect, a method includes: receiving training data for training a machine learning model to perform a particular machine learning task; determining multiple data augmentation policies, comprising, at each of multiple time steps: generating a current data augmentation policy based on quality measures of data augmentation policies generated at previous time steps; training a machine learning model on the training data using the current data augmentation policy; and determining a quality measure of the current data augmentation policy using the machine learning model after it has been trained using the current data augmentation policy; and selecting a final data augmentation policy based on the quality measures of the determined data augmentation policies.Type: ApplicationFiled: May 20, 2019Publication date: November 21, 2019Inventors: Vijay Vasudevan, Barret Zoph, Ekin Dogus Cubuk, Quoc V. Le
-
Publication number: 20190286984Abstract: A method of determining a final architecture for a neural network (NN) for performing a particular NN task is described.Type: ApplicationFiled: March 12, 2019Publication date: September 19, 2019Applicant: Google LLCInventors: Vijay Vasudevan, Mohammad Norouzi, George Edward Dahl, Manoj Kumar Sivaraj
-
Patent number: 10373053Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for receiving, by a computational graph system, a request to process a computational graph; obtaining data representing a subgraph of the computational graph, the computational graph comprising a plurality of nodes and directed edges, wherein each node represents a respective operation, wherein each directed edge connects a respective first node to a respective second node, the subgraph assigned to a first device by a placer in the computational graph system; determining that the first device comprises a hardware accelerator having a plurality of streams; in response to determining, generating instructions that when executed by the first device cause the first device to: assign the operation represented by each node in the subgraph to a respective stream; and perform the operations represented by the nodes in the subgraph in accordance with the assignment.Type: GrantFiled: April 27, 2018Date of Patent: August 6, 2019Assignee: Google LLCInventors: Paul Ronald Barham, Vijay Vasudevan