公开(公告)号：US20240135492A1

公开(公告)日：2024-04-25

申请号：US18379519

申请日：2023-10-12

Applicant: Google LLC

Inventor： Cristina Nader Vasconcelos ,  Ahmet Cengiz Oztireli ,  Andrea Tagliasacchi ,  Kevin Jordan Swersky ,  Mark Jeffrey Matthews ,  Milad Olia Hashemi

IPC: G06T3/40 ,  G06T5/20 ,  G06V10/771

CPC classification number: G06T3/4053 ,  G06T5/20 ,  G06V10/771 ,  G06T2207/10024 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing an input image using a super-resolution neural network to generate an up-sampled image that is a higher resolution version of the input image. In one aspect, a method comprises: processing the input image using an encoder subnetwork of the super-resolution neural network to generate a feature map; generating an updated feature map, comprising, for each spatial position in the updated feature map: applying a convolutional filter to the feature map to generate a plurality of features corresponding to the spatial position in the updated feature map, wherein the convolutional filter is parametrized by a set of convolutional filter parameters that are generated by processing data representing the spatial position using a hyper neural network; and processing the updated feature map using a projection subnetwork of the super-resolution neural network to generate the up-sampled image.

公开(公告)号：US20230342616A1

公开(公告)日：2023-10-26

申请号：US18343579

申请日：2023-06-28

Applicant: Google LLC

Inventor： Ting Chen ,  Simon Komblith ,  Mohammad Norouzi ,  Geoffrey Everest Hinton ,  Kevin Jordan Swersky

IPC: G06N3/084 ,  G06F18/241 ,  G06F18/214 ,  G06V10/774 ,  G06V10/764 ,  G06V10/778 ,  G06N3/08 ,  G06F18/21

CPC classification number: G06N3/084 ,  G06F18/2155 ,  G06F18/2178 ,  G06F18/241 ,  G06N3/08 ,  G06V10/764 ,  G06V10/7753 ,  G06V10/7788 ,  G06T2207/20081

Abstract: Systems, methods, and computer program products for performing semi-supervised contrastive learning of visual representations are provided. For example, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. Further, the present disclosure also provides improvements for semi-supervised contrastive learning. For example, computer-implemented method may include performing semi-supervised contrastive learning based on a set of one or more unlabeled training data, generating an image classification model based on a portion of a plurality of layers in a projection head neural network used in performing the contrastive learning, performing fine-tuning of the image classification model based on a set of one or more labeled training data, and after performing the fine-tuning, distilling the image classification model to a student model comprising a relatively smaller number of parameters than the image classification model.

公开(公告)号：US20230033000A1

公开(公告)日：2023-02-02

申请号：US17887745

申请日：2022-08-15

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/04 ,  G06N3/08 ,  G06F3/06

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.

公开(公告)号：US11386302B2

公开(公告)日：2022-07-12

申请号：US17018372

申请日：2020-09-11

Applicant: Google LLC

Inventor： Ting Chen ,  Simon Kornblith ,  Mohammad Norouzi ,  Geoffrey Everest Hinton ,  Kevin Jordan Swersky

IPC: G06V10/774 ,  G06K9/62 ,  G06N3/08

Abstract: Systems, methods, and computer program products for performing semi-supervised contrastive learning of visual representations are provided. For example, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. Further, the present disclosure also provides improvements for semi-supervised contrastive learning. For example, computer-implemented method may include performing semi-supervised contrastive learning based on a set of one or more unlabeled training data, generating an image classification model based on a portion of a plurality of layers in a projection head neural network used in performing the contrastive learning, performing fine-tuning of the image classification model based on a set of one or more labeled training data, and after performing the fine-tuning, distilling the image classification model to a student model comprising a relatively smaller number of parameters than the image classification model.

公开(公告)号：US12254413B2

公开(公告)日：2025-03-18

申请号：US18343579

申请日：2023-06-28

Applicant: Google LLC

Inventor： Ting Chen ,  Simon Komblith ,  Mohammad Norouzi ,  Geoffrey Everest Hinton ,  Kevin Jordan Swersky

IPC: G06V10/20 ,  G06F18/21 ,  G06F18/214 ,  G06F18/241 ,  G06N3/08 ,  G06N3/084 ,  G06V10/764 ,  G06V10/774 ,  G06V10/778

Abstract: Systems, methods, and computer program products for performing semi-supervised contrastive learning of visual representations are provided. For example, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. Further, the present disclosure also provides improvements for semi-supervised contrastive learning. For example, computer-implemented method may include performing semi-supervised contrastive learning based on a set of one or more unlabeled training data, generating an image classification model based on a portion of a plurality of layers in a projection head neural network used in performing the contrastive learning, performing fine-tuning of the image classification model based on a set of one or more labeled training data, and after performing the fine-tuning, distilling the image classification model to a student model comprising a relatively smaller number of parameters than the image classification model.

公开(公告)号：US12175351B2

公开(公告)日：2024-12-24

申请号：US15994144

申请日：2018-05-31

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Parthasarathy Ranganathan ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/044 ,  G06N3/047 ,  G06N3/063 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for pre-fetching data from memory using neural networks. One example system receives a sequence of prior program counter addresses of a computer program and corresponding delta values. The system creates an input representation based on the sequence. The system provides the input representation as input to a recurrent neural network. The system receives from the recurrent neural network an output that defines a probability distribution over future delta values. Each probability in the distribution represents a likelihood that execution of a future instruction of the computer program will cause data to be fetched from a particular future memory address.

公开(公告)号：US12033056B2

公开(公告)日：2024-07-09

申请号：US17887745

申请日：2022-08-15

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/044 ,  G06F3/06 ,  G06N3/08

CPC classification number: G06N3/044 ,  G06F3/0604 ,  G06F3/0659 ,  G06F3/0673 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.

公开(公告)号：US20250086462A1

公开(公告)日：2025-03-13

申请号：US18960623

申请日：2024-11-26

Applicant: Google LLC

Inventor： Ting Chen ,  Simon Komblith ,  Mohammad Norouzi ,  Geoffrey Everest Hinton ,  Kevin Jordan Swersky

IPC: G06N3/084 ,  G06F18/21 ,  G06F18/214 ,  G06F18/241 ,  G06N3/08 ,  G06V10/764 ,  G06V10/774 ,  G06V10/778

Abstract: Systems, methods, and computer program products for performing semi-supervised contrastive learning of visual representations are provided. For example, the present disclosure provides systems and methods that leverage particular data augmentation schemes and a learnable nonlinear transformation between the representation and the contrastive loss to provide improved visual representations. Further, the present disclosure also provides improvements for semi-supervised contrastive learning. For example, computer-implemented method may include performing semi-supervised contrastive learning based on a set of one or more unlabeled training data, generating an image classification model based on a portion of a plurality of layers in a projection head neural network used in performing the contrastive learning, performing fine-tuning of the image classification model based on a set of one or more labeled training data, and after performing the fine-tuning, distilling the image classification model to a student model comprising a relatively smaller number of parameters than the image classification model.

公开(公告)号：US20250005322A1

公开(公告)日：2025-01-02

申请号：US18737119

申请日：2024-06-07

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/044 ,  G06F3/06 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.

公开(公告)号：US11416733B2

公开(公告)日：2022-08-16

申请号：US16262785

申请日：2019-01-30

Applicant: Google LLC

Inventor： Milad Olia Hashemi ,  Jamie Alexander Smith ,  Kevin Jordan Swersky

IPC: G06N3/04 ,  G06N3/08 ,  G06F3/06

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, relating to multi-task recurrent neural networks. One of the methods includes maintaining data specifying, for a recurrent neural network, a separate internal state for each of a plurality of memory regions; receiving a current input; identifying a particular memory region of the memory access address defined by the current input; selecting, from the internal states specified in the maintained data, the internal state for the particular memory region; processing, in accordance with the selected internal state for the particular memory region, the current input in the sequence of inputs using the recurrent neural network to: generate an output, the output defining a probability distribution of a predicted memory access address, and update the selected internal state of the particular memory region; and associating the updated selected internal state with the particular memory region in the maintained data.