公开(公告)号：US11205099B2

公开(公告)日：2021-12-21

申请号：US16833449

申请日：2020-03-27

Applicant: Google LLC

Inventor： Jonathon Shlens ,  Quoc V. Le ,  Ekin Dogus Cubuk ,  Barret Zoph

IPC: G06K9/62 ,  G06N3/08 ,  G06N3/04

Abstract: 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.

公开(公告)号：US20210334624A1

公开(公告)日：2021-10-28

申请号：US17365939

申请日：2021-07-01

Applicant: Google LLC

Inventor： Wei Hua ,  Barret Zoph ,  Jonathon Shlens ,  Chenxi Liu ,  Jonathan Huang ,  Jia Li ,  Fei-Fei Li ,  Kevin Patrick Murphy

IPC: G06N3/04 ,  G06K9/62 ,  G06N3/063 ,  G06N3/08

Abstract: A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described. The method includes obtaining data specifying a current set of candidate architectures for the task neural network; for each candidate architecture in the current set: processing the data specifying the candidate architecture using a performance prediction neural network having multiple performance prediction parameters, the performance prediction neural network being configured to process the data specifying the candidate architecture in accordance with current values of the performance prediction parameters to generate a performance prediction that characterizes how well a neural network having the candidate architecture would perform after being trained on the particular machine learning task; and generating an updated set of candidate architectures by selecting one or more of the candidate architectures in the current set based on the performance predictions for the candidate architectures in the current set.

公开(公告)号：US20210271970A1

公开(公告)日：2021-09-02

申请号：US17145524

申请日：2021-01-11

Applicant: Google LLC

Inventor： Irwan Bello ,  Barret Zoph ,  Vijay Vasudevan ,  Quoc V. Le

IPC: G06N3/08 ,  G06N3/04

Abstract: 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.

公开(公告)号：US20200257961A1

公开(公告)日：2020-08-13

申请号：US16861491

申请日：2020-04-29

Applicant: Google LLC

Inventor： Wei Hua ,  Barret Zoph ,  Jonathon Shlens ,  Chenxi Liu ,  Jonathan Huang ,  Jia Li ,  Fei-Fei Li ,  Kevin Patrick Murphy

IPC: G06N3/04 ,  G06N3/063 ,  G06N3/08 ,  G06K9/62

Abstract: A method for determining an architecture for a task neural network configured to perform a particular machine learning task is described. The method includes obtaining data specifying a current set of candidate architectures for the task neural network; for each candidate architecture in the current set: processing the data specifying the candidate architecture using a performance prediction neural network having multiple performance prediction parameters, the performance prediction neural network being configured to process the data specifying the candidate architecture in accordance with current values of the performance prediction parameters to generate a performance prediction that characterizes how well a neural network having the candidate architecture would perform after being trained on the particular machine learning task; and generating an updated set of candidate architectures by selecting one or more of the candidate architectures in the current set based on the performance predictions for the candidate architectures in the current set.

公开(公告)号：US20190370648A1

公开(公告)日：2019-12-05

申请号：US16425900

申请日：2019-05-29

Applicant: Google LLC

Inventor： Barret Zoph ,  Jonathon Shlens ,  Yukun Zhu ,  Maxwell Donald Emmet Collins ,  Liang-Chieh Chen ,  Gerhard Florian Schroff ,  Hartwig Adam ,  Georgios Papandreou

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06N20/00 ,  G06F17/15

Abstract: 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.

公开(公告)号：US20240242125A1

公开(公告)日：2024-07-18

申请号：US18584625

申请日：2024-02-22

Applicant: Google LLC

Inventor： Vijay Vasudevan ,  Barret Zoph ,  Ekin Dogus Cubuk ,  Quoc V. Le

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: 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.

公开(公告)号：US11816577B2

公开(公告)日：2023-11-14

申请号：US17487548

申请日：2021-09-28

Applicant: Google LLC

Inventor： Daniel Sung-Joon Park ,  Quoc Le ,  William Chan ,  Ekin Dogus Cubuk ,  Barret Zoph ,  Yu Zhang ,  Chung-Cheng Chiu

IPC: G10L15/06 ,  G10L15/12 ,  G06N3/084 ,  G10L15/16 ,  G10L15/28 ,  G06N20/00 ,  G06F18/214 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06N3/084 ,  G06F18/2148 ,  G06N20/00 ,  G06V10/7747 ,  G06V10/82 ,  G10L15/063 ,  G10L15/12 ,  G10L15/16 ,  G10L15/28

Abstract: 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.

公开(公告)号：US20230351188A1

公开(公告)日：2023-11-02

申请号：US18349089

申请日：2023-07-07

Applicant: Google LLC

Inventor： William Bradley Fedus ,  Barret Zoph ,  Noam M. Shazeer

IPC: G06N3/082 ,  G06N3/045

CPC classification number: G06N3/082 ,  G06N3/045

Abstract: 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.

公开(公告)号：US11682191B2

公开(公告)日：2023-06-20

申请号：US17702438

申请日：2022-03-23

Applicant: Google LLC

Inventor： Jon Shlens ,  Ekin Dogus Cubuk ,  Quoc Le ,  Tsung-Yi Lin ,  Barret Zoph ,  Golnaz Ghiasi

IPC: G06V10/772 ,  G06T3/60 ,  G06T3/20 ,  G06T11/00 ,  G06F18/24 ,  G06F18/21

CPC classification number: G06V10/772 ,  G06F18/217 ,  G06F18/24 ,  G06T3/20 ,  G06T3/60 ,  G06T11/001

Abstract: 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.

公开(公告)号：US11651259B2

公开(公告)日：2023-05-16

申请号：US16674801

申请日：2019-11-05

Applicant: Google LLC

Inventor： Vijay Vasudevan ,  Barret Zoph ,  Jonathon Shlens ,  Quoc V. Le

IPC: G06N5/04 ,  G06N3/04 ,  G06N3/08 ,  G06T7/00 ,  G06N5/046

CPC classification number: G06N5/046 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/08 ,  G06T7/0002 ,  G06T2207/20084

Abstract: 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.