公开(公告)号：US20220215682A1

公开(公告)日：2022-07-07

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: G06V30/194 ,  G06K9/62 ,  G06T3/60 ,  G06T3/20 ,  G06T11/00

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：US11087201B2

公开(公告)日：2021-08-10

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 ,  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：US11030523B2

公开(公告)日：2021-06-08

申请号：US16397641

申请日：2019-04-29

Applicant: Google LLC

Inventor： Barret Zoph ,  Quoc V. Le

IPC: G06N3/08 ,  G06N3/04

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, 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.

公开(公告)号：US10984319B2

公开(公告)日：2021-04-20

申请号：US16859781

申请日：2020-04-27

Applicant: Google LLC

Inventor： Barret Zoph ,  Yun Jia Guan ,  Hieu Hy Pham ,  Quoc V. Le

IPC: G06N3/08 ,  G06N3/04

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, 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.

公开(公告)号：US10922611B2

公开(公告)日：2021-02-16

申请号：US16662924

申请日：2019-10-24

Applicant: Google LLC

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

IPC: G06N3/00 ,  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：US10817805B2

公开(公告)日：2020-10-27

申请号：US16417133

申请日：2019-05-20

Applicant: Google LLC

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

IPC: 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：US20200265315A1

公开(公告)日：2020-08-20

申请号：US16859781

申请日：2020-04-27

Applicant: Google LLC

Inventor： Barret Zoph ,  Yun Jia Guan ,  Hieu Hy Pham ,  Quoc V. Le

IPC: G06N3/08 ,  G06N3/04

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, 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.

公开(公告)号：US20200057941A1

公开(公告)日：2020-02-20

申请号：US16662924

申请日：2019-10-24

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：US20190354808A1

公开(公告)日：2019-11-21

申请号：US16416888

申请日：2019-05-20

Applicant: Google LLC

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

IPC: G06K9/62 ,  G10L15/16 ,  G06N20/00 ,  G10L15/06 ,  G10L15/12 ,  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.