Systems and Methods for Machine-Learned Models Having Convolution and Attention

    公开(公告)号:US20220383069A1

    公开(公告)日:2022-12-01

    申请号:US17827130

    申请日:2022-05-27

    Applicant: Google LLC

    Abstract: A computer-implemented method for performing computer vision with reduced computational cost and improved accuracy can include obtaining, by a computing system including one or more computing devices, input data comprising an input tensor having one or more dimensions, providing, by the computing system, the input data to a machine-learned convolutional attention network, the machine-learned convolutional attention network including two or more network stages, and, in response to providing the input data to the machine-learned convolutional attention network, receiving, by the computing system, a machine-learning prediction from the machine-learned convolutional attention network. The convolutional attention network can include at least one attention block, wherein the attention block includes a relative attention mechanism, the relative attention mechanism including the sum of a static convolution kernel with an adaptive attention matrix. This provides for improved generalization, capacity, and efficiency of the convolutional attention network relative to some existing models.

    TRAINING MACHINE LEARNING MODELS USING UNSUPERVISED DATA AUGMENTATION

    公开(公告)号:US20220215209A1

    公开(公告)日:2022-07-07

    申请号:US17606190

    申请日:2020-04-24

    Applicant: Google LLC

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a IT machine learning model. One of the methods includes receiving training data comprising a plurality of unlabeled training inputs and a plurality of labeled training inputs; generating augmented training data, comprising generating, for each of the plurality of unlabeled training inputs, a respective augmented training input by applying a data augmentation technique to the unlabeled training input; and training the machine learning model on the augmented training data. In particular, but not exclusively, the model may be trained for perceptual tasks (e.g. tasks relating to vision or speech).

    Systems and methods for machine-learned models having convolution and attention

    公开(公告)号:US11755883B2

    公开(公告)日:2023-09-12

    申请号:US17827130

    申请日:2022-05-27

    Applicant: Google LLC

    CPC classification number: G06N3/044 G06N3/063 G06N3/08 G06N20/00

    Abstract: A computer-implemented method for performing computer vision with reduced computational cost and improved accuracy can include obtaining, by a computing system including one or more computing devices, input data comprising an input tensor having one or more dimensions, providing, by the computing system, the input data to a machine-learned convolutional attention network, the machine-learned convolutional attention network including two or more network stages, and, in response to providing the input data to the machine-learned convolutional attention network, receiving, by the computing system, a machine-learning prediction from the machine-learned convolutional attention network. The convolutional attention network can include at least one attention block, wherein the attention block includes a relative attention mechanism, the relative attention mechanism including the sum of a static convolution kernel with an adaptive attention matrix. This provides for improved generalization, capacity, and efficiency of the convolutional attention network relative to some existing models.

    ATTENTION NEURAL NETWORKS WITH GATED ATTENTION UNITS

    公开(公告)号:US20250139431A1

    公开(公告)日:2025-05-01

    申请号:US18834202

    申请日:2023-01-30

    Applicant: Google LLC

    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 attentive layers that each include a gated attention unit.

    Training machine learning models using unsupervised data augmentation

    公开(公告)号:US12118064B2

    公开(公告)日:2024-10-15

    申请号:US17606190

    申请日:2020-04-24

    Applicant: Google LLC

    CPC classification number: G06F18/217 G06F18/2148 G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a IT machine learning model. One of the methods includes receiving training data comprising a plurality of unlabeled training inputs and a plurality of labeled training inputs; generating augmented training data, comprising generating, for each of the plurality of unlabeled training inputs, a respective augmented training input by applying a data augmentation technique to the unlabeled training input; and training the machine learning model on the augmented training data. In particular, but not exclusively, the model may be trained for perceptual tasks (e.g. tasks relating to vision or speech).

    Systems and Methods for Machine-Learned Models Having Convolution and Attention

    公开(公告)号:US20230359862A1

    公开(公告)日:2023-11-09

    申请号:US18355243

    申请日:2023-07-19

    Applicant: Google LLC

    CPC classification number: G06N3/044 G06N20/00 G06N3/063 G06N3/08

    Abstract: A computer-implemented method for performing computer vision with reduced computational cost and improved accuracy can include obtaining, by a computing system including one or more computing devices, input data comprising an input tensor having one or more dimensions, providing, by the computing system, the input data to a machine-learned convolutional attention network, the machine-learned convolutional attention network including two or more network stages, and, in response to providing the input data to the machine-learned convolutional attention network, receiving, by the computing system, a machine-learning prediction from the machine-learned convolutional attention network. The convolutional attention network can include at least one attention block, wherein the attention block includes a relative attention mechanism, the relative attention mechanism including the sum of a static convolution kernel with an adaptive attention matrix. This provides for improved generalization, capacity, and efficiency of the convolutional attention network relative to some existing models.

    Systems and Methods for Pretraining Image Processing Models

    公开(公告)号:US20230281400A1

    公开(公告)日:2023-09-07

    申请号:US17685774

    申请日:2022-03-03

    Applicant: Google LLC

    CPC classification number: G06F40/58 G06F40/284 G06V10/766 G06V30/10

    Abstract: Example embodiments of the present disclosure relate to systems and methods for pretraining image-processing models on weakly-supervised image-text pairs. The pretraining can include receiving a training sequence for the machine-learned image-processing model. The training sequence can include text tokens and image tokens. A prefix sequence can contain the image tokens. A remainder sequence can include a remainder set of the text tokens. The pretraining can include determining, using the prefix sequence as an input to the machine-learned image-processing model, an objective based on recovery of the remainder sequence. The pretraining can include updating one or more learnable parameters of the machine-learned image-processing model based on the objective.

Patent Agency Ranking