-
公开(公告)号：US11138471B2
公开(公告)日：2021-10-05
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
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：US20210232929A1
公开(公告)日：2021-07-29
申请号：US17232803
申请日：2021-04-16
Applicant: Google LLC
Inventor： Barret Zoph , Yun Jia Guan , Hieu Hy Pham , Quoc V. Le
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：US20210081796A1
公开(公告)日：2021-03-18
申请号：US17107745
申请日：2020-11-30
Applicant: Google LLC
Inventor： Barret Zoph , Jonathon Shlens , Yukun Zhu , Maxwell Donald Collins , Liang-Chieh Chen , Gerhard Florian Schroff , Hartwig Adam , Georgios Papandreou
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：US10853726B2
公开(公告)日：2020-12-01
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
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：US20190354895A1
公开(公告)日：2019-11-21
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.
-
Patent Agency Ranking
公开(公告)号：US20190354817A1
公开(公告)日：2019-11-21
申请号：US16416848
申请日：2019-05-20
Applicant: Google LLC
Inventor： Jon Shlens , Ekin Dogus Cubuk , Quoc Le , Tsung-Yi Lin , Barret Zoph , Golnaz Ghiasi
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：US12293266B2
公开(公告)日：2025-05-06
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
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：US12093829B2
公开(公告)日：2024-09-17
申请号：US18349089
申请日：2023-07-07
Applicant: Google LLC
Inventor： William Bradley Fedus , Barret Zoph , Noam M. Shazeer
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：US11829874B2
公开(公告)日：2023-11-28
申请号：US17340959
申请日：2021-06-07
Applicant: Google LLC
Inventor： Barret Zoph , Quoc V. Le
CPC classification number: G06N3/08 , G06F18/217 , G06N3/044 , G06N3/045
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：US20230274532A1
公开(公告)日：2023-08-31
申请号：US18313772
申请日：2023-05-08
Applicant: Google LLC
Inventor： Jon Shlens , Ekin Dogus Cubuk , Quoc Le , Tsung-Yi Lin , Barret Zoph , Golnaz Ghiasi
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.
-
-
-
-
-
-
-
-
-
Search Results
49
records
(took 0.015 seconds)
