Patents by Inventor Barret Zoph
Barret Zoph 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: 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: 11087201Abstract: A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described.Type: GrantFiled: April 29, 2020Date of Patent: August 10, 2021Assignee: Google LLCInventors: Wei Hua, Barret Zoph, Jonathon Shlens, Chenxi Liu, Jonathan Huang, Jia Li, Fei-Fei Li, Kevin Patrick Murphy
-
Publication number: 20210232929Abstract: 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, a batch of output sequences, each output sequence in the batch specifying a respective subset of a plurality of components of a large neural network that should be active during the processing of inputs by the large neural network; for each output sequence in the batch: determining a performance metric of the large neural network on the particular neural network task (i) in accordance with current values of the large network parameters and (ii) with only the subset of components specified by the output sequences active; and using the performance metrics for the output sequences in the batch to adjust the current values of the controller parameters of the controller neural network.Type: ApplicationFiled: April 16, 2021Publication date: July 29, 2021Inventors: Barret Zoph, Yun Jia Guan, Hieu Hy Pham, Quoc V. Le
-
Patent number: 11030523Abstract: 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, a batch of output sequences, each output sequence in the batch defining a respective architecture of a child neural network that is configured to perform a particular neural network task; for each output sequence in the batch: training a respective instance of the child neural network having the architecture 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: April 29, 2019Date of Patent: June 8, 2021Assignee: Google LLCInventors: Barret Zoph, Quoc V. Le
-
Patent number: 10984319Abstract: 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, a batch of output sequences, each output sequence in the batch specifying a respective subset of a plurality of components of a large neural network that should be active during the processing of inputs by the large neural network; for each output sequence in the batch: determining a performance metric of the large neural network on the particular neural network task (i) in accordance with current values of the large network parameters and (ii) with only the subset of components specified by the output sequences active; and using the performance metrics for the output sequences in the batch to adjust the current values of the controller parameters of the controller neural network.Type: GrantFiled: April 27, 2020Date of Patent: April 20, 2021Assignee: Google LLCInventors: Barret Zoph, Yun Jia Guan, Hieu Hy Pham, Quoc V. Le
-
Publication number: 20210097348Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model. One of the methods includes obtaining a training data set for training a machine learning model, the training data set comprising a plurality of training inputs; determining a plurality of data augmentation policies, wherein each data augmentation policy defines a procedure for processing a training input to generate a transformed training input; for each data augmentation policy, training the machine learning model using the data augmentation policy; determining, for each data augmentation policy, a quality measure of the machine learning model that has been trained using the data augmentation policy; and selecting a final data augmentation policy based using the quality measures of the machine learning models.Type: ApplicationFiled: March 27, 2020Publication date: April 1, 2021Inventors: Jonathon Shlens, Quoc V. Le, Ekin Dogus Cubuk, Barret Zoph
-
Publication number: 20210081796Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.Type: ApplicationFiled: November 30, 2020Publication date: March 18, 2021Inventors: Barret Zoph, Jonathon Shlens, Yukun Zhu, Maxwell Donald Collins, Liang-Chieh Chen, Gerhard Florian Schroff, Hartwig Adam, Georgios Papandreou
-
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
-
Patent number: 10853726Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.Type: GrantFiled: May 29, 2019Date of Patent: December 1, 2020Assignee: Google LLCInventors: Barret Zoph, Jonathon Shlens, Yukun Zhu, Maxwell Donald Emmet Collins, Liang-Chieh Chen, Gerhard Florian Schroff, Hartwig Adam, Georgios Papandreou
-
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
-
Publication number: 20200265315Abstract: 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, a batch of output sequences, each output sequence in the batch specifying a respective subset of a plurality of components of a large neural network that should be active during the processing of inputs by the large neural network; for each output sequence in the batch: determining a performance metric of the large neural network on the particular neural network task (i) in accordance with current values of the large network parameters and (ii) with only the subset of components specified by the output sequences active; and using the performance metrics for the output sequences in the batch to adjust the current values of the controller parameters of the controller neural network.Type: ApplicationFiled: April 27, 2020Publication date: August 20, 2020Inventors: Barret Zoph, Yun Jia Guan, Hieu Hy Pham, Quoc V. Le
-
Publication number: 20200257961Abstract: A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described.Type: ApplicationFiled: April 29, 2020Publication date: August 13, 2020Inventors: Wei Hua, Barret Zoph, Jonathon Shlens, Chenxi Liu, Jonathan Huang, Jia Li, Fei-Fei Li, Kevin Patrick Murphy
-
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: 20190370648Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes obtaining training data for a dense image prediction task; and determining an architecture for a neural network configured to perform the dense image prediction task, comprising: searching a space of candidate architectures to identify one or more best performing architectures using the training data, wherein each candidate architecture in the space of candidate architectures comprises (i) the same first neural network backbone that is configured to receive an input image and to process the input image to generate a plurality of feature maps and (ii) a different dense prediction cell configured to process the plurality of feature maps and to generate an output for the dense image prediction task; and determining the architecture for the neural network based on the best performing candidate architectures.Type: ApplicationFiled: May 29, 2019Publication date: December 5, 2019Inventors: Barret Zoph, Jonathon Shlens, Yukun Zhu, Maxwell Donald Emmet Collins, Liang-Chieh Chen, Gerhard Florian Schroff, Hartwig Adam, Georgios Papandreou
-
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: 20190354808Abstract: Generally, the present disclosure is directed to systems and methods that generate augmented training data for machine-learned models via application of one or more augmentation techniques to audiographic images that visually represent audio signals. In particular, the present disclosure provides a number of novel augmentation operations which can be performed directly upon the audiographic image (e.g., as opposed to the raw audio data) to generate augmented training data that results in improved model performance. As an example, the audiographic images can be or include one or more spectrograms or filter bank sequences.Type: ApplicationFiled: May 20, 2019Publication date: November 21, 2019Inventors: Daniel Sung-Joon Park, Quoc Le, William Chan, Ekin Dogus Cubuk, Barret Zoph, Yu Zhang, Chung-Cheng Chiu
-
Publication number: 20190354817Abstract: Example aspects of the present disclosure are directed to systems and methods for learning data augmentation strategies for improved object detection model performance. In particular, example aspects of the present disclosure are directed to iterative reinforcement learning approaches in which, at each of a plurality of iterations, a controller model selects a series of one or more augmentation operations to be applied to training images to generate augmented images. For example, the controller model can select the augmentation operations from a defined search space of available operations which can, for example, include operations that augment the training image without modification of the locations of a target object and corresponding bounding shape within the image and/or operations that do modify the locations of the target object and bounding shape within the training image.Type: ApplicationFiled: May 20, 2019Publication date: November 21, 2019Inventors: Jon Shlens, Ekin Dogus Cubuk, Quoc Le, Tsung-Yi Lin, Barret Zoph, Golnaz Ghiasi