公开(公告)号：US20210056162A1

公开(公告)日：2021-02-25

申请号：US16989455

申请日：2020-08-10

Applicant: Google LLC

Inventor： Mostafa Dehghani ,  Stephan Gouws ,  Oriol Vinyals ,  Jakob D. Uszkoreit ,  Lukasz Mieczyslaw Kaiser

IPC: G06F17/14 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a sequence to sequence model that is recurrent in depth while employing self-attention to combine information from different parts of sequences.

公开(公告)号：US10740433B2

公开(公告)日：2020-08-11

申请号：US16417587

申请日：2019-05-20

Applicant: Google LLC

Inventor： Mostafa Dehghani ,  Stephan Gouws ,  Oriol Vinyals ,  Jakob D. Uszkoreit ,  Lukasz Mieczyslaw Kaiser

IPC: G06F17/00 ,  G06F17/14 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a sequence to sequence model that is recurrent in depth while employing self-attention to combine information from different parts of sequences.

公开(公告)号：US12125247B2

公开(公告)日：2024-10-22

申请号：US17492537

申请日：2021-10-01

Applicant: Google LLC

Inventor： Neil Matthew Tinmouth Houlsby ,  Sylvain Gelly ,  Jakob D. Uszkoreit ,  Xiaohua Zhai ,  Georg Heigold ,  Lucas Klaus Beyer ,  Alexander Kolesnikov ,  Matthias Johannes Lorenz Minderer ,  Dirk Weissenborn ,  Mostafa Dehghani ,  Alexey Dosovitskiy ,  Thomas Unterthiner

IPC: G06T7/00 ,  G06F18/24 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06T7/97 ,  G06F18/24 ,  G06N3/045 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using self-attention based neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more self-attention neural network layers.

公开(公告)号：US20240169184A1

公开(公告)日：2024-05-23

申请号：US18426212

申请日：2024-01-29

Applicant: Google LLC

Inventor： Tal Schuster ,  Adam Joshua Fisch ,  Jai Prakash Gupta ,  Mostafa Dehghani ,  Dara Bahri ,  Vinh Quoc Tran ,  Yi Tay ,  Donald Arthur Metzler, JR.

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output sequences using auto-regressive decoder neural networks. In particular, during generation, adaptive early exiting is used to reduce the time required to generate the output sequence.

公开(公告)号：US20240062426A1

公开(公告)日：2024-02-22

申请号：US18500034

申请日：2023-11-01

Applicant: Google LLC

Inventor： Neil Matthew Tinmouth Houlsby ,  Sylvain Gelly ,  Jakob D. Uszkoreit ,  Xiaohua Zhai ,  Georg Heigold ,  Lucas Klaus Beyer ,  Alexander Kolesnikov ,  Matthias Johannes Lorenz Minderer ,  Dirk Weissenborn ,  Mostafa Dehghani ,  Alexey Dosovitskiy ,  Thomas Unterthiner

IPC: G06T7/00 ,  G06F18/24 ,  G06N3/045 ,  G06N3/08

CPC classification number: G06T7/97 ,  G06F18/24 ,  G06N3/045 ,  G06N3/08 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using self-attention based neural networks. One of the methods includes obtaining one or more images comprising a plurality of pixels; determining, for each image of the one or more images, a plurality of image patches of the image, wherein each image patch comprises a different subset of the pixels of the image; processing, for each image of the one or more images, the corresponding plurality of image patches to generate an input sequence comprising a respective input element at each of a plurality of input positions, wherein a plurality of the input elements correspond to respective different image patches; and processing the input sequences using a neural network to generate a network output that characterizes the one or more images, wherein the neural network comprises one or more self-attention neural network layers.

公开(公告)号：US20240020516A1

公开(公告)日：2024-01-18

申请号：US18222395

申请日：2023-07-14

Applicant: Google LLC

Inventor： Tal Schuster ,  Adam Joshua Fisch ,  Jai Prakash Gupta ,  Mostafa Dehghani ,  Dara Bahri ,  Vinh Quoc Tran ,  Yi Tay ,  Donald Arthur Metzler, Jr.

IPC: G06N3/0455

CPC classification number: G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating output sequences using auto-regressive decoder neural networks. In particular, during generation, adaptive early exiting is used to reduce the time required to generate the output sequence.

公开(公告)号：US11860969B2

公开(公告)日：2024-01-02

申请号：US16989455

申请日：2020-08-10

Applicant: Google LLC

Inventor： Mostafa Dehghani ,  Stephan Gouws ,  Oriol Vinyals ,  Jakob D. Uszkoreit ,  Lukasz Mieczyslaw Kaiser

IPC: G06N3/04 ,  G06F17/14

CPC classification number: G06F17/14 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a sequence to sequence model that is recurrent in depth while employing self-attention to combine information from different parts of sequences.

公开(公告)号：US20230409899A1

公开(公告)日：2023-12-21

申请号：US17845753

申请日：2022-06-21

Applicant: Google LLC

Inventor： Michael Sahngwon Ryoo ,  Anthony Jacob Piergiovanni ,  Anelia Angelova ,  Anurag Arnab ,  Mostafa Dehghani

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing a network input using a computer vision neural network with learned tokenization.

公开(公告)号：US20230031702A1

公开(公告)日：2023-02-02

申请号：US17812208

申请日：2022-07-13

Applicant: Google LLC

Inventor： Yang Li ,  Xin Zhou ,  Gang Li ,  Mostafa Dehghani ,  Alexey Alexeevich Gritsenko

IPC: G06V10/82 ,  G06F3/16 ,  G06F40/284

Abstract: A method includes receiving, via a computing device, a screenshot of a display provided by a graphical user interface of the computing device. The method also includes generating, by an image-structure transformer of a neural network, a representation by fusing a first embedding based on the screenshot and a second embedding based on a layout of virtual objects in the screenshot. The method additionally includes predicting, by the neural network and based on the generated representation, a modeling task output associated with the graphical user interface. The method further includes providing, by the computing device, the predicted modeling task output.