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).
-
Patent number: 11847541Abstract: 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: GrantFiled: December 20, 2021Date of Patent: December 19, 2023Assignee: Google LLCInventors: Jonathon Shlens, Quoc V. Le, Ekin Dogus Cubuk, Barret Zoph
-
Patent number: 11829874Abstract: 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: June 7, 2021Date of Patent: November 28, 2023Assignee: Google LLCInventors: Barret Zoph, Quoc V. Le
-
Publication number: 20230368024Abstract: 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: ApplicationFiled: July 26, 2023Publication date: November 16, 2023Inventors: Barret Zoph, Quoc V. Le
-
Patent number: 11816577Abstract: 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: GrantFiled: September 28, 2021Date of Patent: November 14, 2023Assignee: GOOGLE LLCInventors: Daniel Sung-Joon Park, Quoc Le, William Chan, Ekin Dogus Cubuk, Barret Zoph, Yu Zhang, Chung-Cheng Chiu
-
Publication number: 20230359898Abstract: 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: July 11, 2023Publication date: November 9, 2023Inventors: Daniel Sung-Joon Park, Quoc Le, William Chan, Ekin Dogus Cubuk, Barret Zoph, Yu Zhang, Chung-Cheng Chiu
-
Publication number: 20230351188Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more switch layers.Type: ApplicationFiled: July 7, 2023Publication date: November 2, 2023Inventors: William Bradley Fedus, Barret Zoph, Noam M. Shazeer
-
Publication number: 20230274532Abstract: 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 8, 2023Publication date: August 31, 2023Inventors: Jon Shlens, Ekin Dogus Cubuk, Quoc Le, Tsung-Yi Lin, Barret Zoph, Golnaz Ghiasi
-
Publication number: 20230252327Abstract: 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: April 20, 2023Publication date: August 10, 2023Inventors: Vijay Vasudevan, Barret Zoph, Jonathon Shlens, Quoc V. Le
-
Patent number: 11682191Abstract: 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: GrantFiled: March 23, 2022Date of Patent: June 20, 2023Assignee: GOOGLE LLCInventors: Jon Shlens, Ekin Dogus Cubuk, Quoc Le, Tsung-Yi Lin, Barret Zoph, Golnaz Ghiasi
-
Patent number: 11651259Abstract: 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: November 5, 2019Date of Patent: May 16, 2023Assignee: Google LLCInventors: Vijay Vasudevan, Barret Zoph, Jonathon Shlens, Quoc V. Le
-
Publication number: 20220301298Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an image representation neural network.Type: ApplicationFiled: March 17, 2022Publication date: September 22, 2022Inventors: Tsung-Yi Lin, Barret Zoph, Ekin Dogus Cubuk, Golnaz Ghiasi, Quoc V. Le
-
Publication number: 20220215682Abstract: 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: March 23, 2022Publication date: July 7, 2022Inventors: Jon Shlens, Ekin Dogus Cubuk, Quoc Le, Tsung-Yi Lin, Barret Zoph, Golnaz Ghiasi
-
Publication number: 20220114400Abstract: 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: December 20, 2021Publication date: April 14, 2022Inventors: Jonathon Shlens, Quoc V. Le, Ekin Dogus Cubuk, Barret Zoph
-
Patent number: 11301733Abstract: 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: GrantFiled: May 20, 2019Date of Patent: April 12, 2022Assignee: GOOGLE LLCInventors: Jon Shlens, Ekin Dogus Cubuk, Quoc Le, Tsung-Yi Lin, Barret Zoph, Golnaz Ghiasi
-
Publication number: 20220012537Abstract: 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: September 28, 2021Publication date: January 13, 2022Inventors: Daniel Sung-Joon Park, Quoc V. Le, William Chan, Ekin Dogus Cubuk, Barret Zoph, Yu Zhang, Chung-Cheng Chiu
-
Patent number: 11205099Abstract: 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: GrantFiled: March 27, 2020Date of Patent: December 21, 2021Assignee: Google LLCInventors: Jonathon Shlens, Quoc V. Le, Ekin Dogus Cubuk, Barret Zoph
-
Publication number: 20210334651Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model to perform a machine learning task by processing input data to the model. For example, the input data can include image, video, or point cloud data, and the task can be a perception task such as classification or detection task. In one aspect, the method includes receiving training data including a plurality of training inputs; receiving a plurality of data augmentation policy parameters that define different transformation operations for transforming training inputs before the training inputs are used to train the machine learning model; maintaining a plurality of candidate machine learning models; for each of the plurality of candidate machine learning models: repeatedly determining an augmented batch of training data; training the candidate machine learning model using the augmented batch of the training data; and updating the maintained data.Type: ApplicationFiled: March 5, 2021Publication date: October 28, 2021Inventors: Zhaoqi Leng, Ekin Dogus Cubuk, Barret Zoph, Jiquan Ngiam, Congcong Li, Jonathon Shlens, Shuyang Cheng
-
Publication number: 20210334624Abstract: A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described.Type: ApplicationFiled: July 1, 2021Publication date: October 28, 2021Inventors: Wei Hua, Barret Zoph, Jonathon Shlens, Chenxi Liu, Jonathan Huang, Jia Li, Fei-Fei Li, Kevin Patrick Murphy
-
Patent number: 11138471Abstract: 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: GrantFiled: May 20, 2019Date of Patent: October 5, 2021Assignee: Google LLCInventors: Daniel Sung-Joon Park, Quoc Le, William Chan, Ekin Dogus Cubuk, Barret Zoph, Yu Zhang, Chung-Cheng Chiu
-
Publication number: 20210295163Abstract: 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: ApplicationFiled: June 7, 2021Publication date: September 23, 2021Inventors: Barret Zoph, Quoc V. Le