公开(公告)号：US11144831B2

公开(公告)日：2021-10-12

申请号：US16906034

申请日：2020-06-19

Applicant: Google LLC

Inventor： Yanping Huang ,  Alok Aggarwal ,  Quoc V. Le ,  Esteban Alberto Real

IPC: G06F15/18 ,  G06N3/00 ,  G06N3/12 ,  G06N3/08 ,  G06N3/04

Abstract: A method for receiving training data for training a neural network (NN) to perform a machine learning (ML) task and for determining, using the training data, an optimized NN architecture for performing the ML task is described. Determining the optimized NN architecture includes: maintaining population data comprising, for each candidate architecture in a population of candidate architectures, (i) data defining the candidate architecture, and (ii) data specifying how recently a neural network having the candidate architecture has been trained while determining the optimized neural network architecture; and repeatedly performing multiple operations using each of a plurality of worker computing units to generate a new candidate architecture based on a selected candidate architecture having the best measure of fitness, adding the new candidate architecture to the population, and removing from the population the candidate architecture that was trained least recently.

公开(公告)号：USD1042527S1

公开(公告)日：2024-09-17

申请号：US29869038

申请日：2022-12-20

Applicant: Google LLC

Designer： Jessica Lee ,  Alok Aggarwal ,  Ruslan Alfridovich Abdikeev ,  Jessica Katherine Turner ,  Wenjia Yuan ,  Hassan Ali Shojania ,  Viviana Caso Corella ,  Harshit Kharbanda

Abstract: FIG. 1 is a front view of a display screen or portion thereof with a transitional graphical user interface showing a first image of the claimed design;
FIG. 2 is a second image thereof; and,
FIG. 3 is a third image thereof.
The outermost evenly spaced broken lines show an electronic device that forms no part of the claimed design. The dot-dash broken lines show a display screen or portion thereof and form no part of the claimed design. The remaining broken lines and all lined-through text, show portions of the transitional graphical user interface, and form no part of the claimed design.
The appearance of the transitional image sequentially transitions between the views of FIGS. 1-3. The process or period in which an image transitions to another forms no part of the claimed design.

公开(公告)号：US11080762B1

公开(公告)日：2021-08-03

申请号：US15211240

申请日：2016-07-15

Applicant: Google LLC

Inventor： Ali Nasiri Amini ,  Ardian Poernomo ,  Alireza Darvish ,  Alok Aggarwal ,  Eu-Jin Goh ,  Oren E. Zamir ,  Qing Xu

IPC: G06Q30/00 ,  G06Q30/02 ,  G06F16/22

Abstract: Methods, systems, and apparatus for content item auction bidding. In one aspect, a method includes receiving a request for a content item, the request including request feature values and a device identifier, the device identifier being included in a remarketing list; obtaining a predicted performance measure for a remarketing content item associated with the remarketing list based on a first timestamp and a second timestamp, the first timestamp being included in the remarketing list and associated with the device identifier included in the request, and the second timestamp being for the request; determining a bid adjustment value based on the first timestamp and the second timestamp; obtaining a remarketing bid for the remarketing content item, the remarketing bid specifying an amount a content item provider is willing to pay for distribution of the remarketing content item; and adjusting the remarketing bid based on the bid adjustment value.

公开(公告)号：US12230030B2

公开(公告)日：2025-02-18

申请号：US18084710

申请日：2022-12-20

Applicant: Google LLC

Inventor： Jessica Lee ,  Christopher James Kelley ,  Alok Aggarwal ,  Harshit Kharbanda

IPC: G06V20/20 ,  G06F16/9535 ,  G06T11/00 ,  G06V10/94

Abstract: Systems and methods for providing scene understanding can include obtaining a plurality of images, stitching images associated with the scene, detecting objects in the scene, and providing information associated with the objects in the scene. The systems and methods can include determining filter tags or query tags that can be selected to filter the plurality of objects, which can then be provided as information to the user to provide further insight on the scene. The information may be provided in an augmented-reality experience via text or other user-interface elements anchored to objects in the images.

公开(公告)号：US20230368527A1

公开(公告)日：2023-11-16

申请号：US18084710

申请日：2022-12-20

Applicant: Google LLC

Inventor： Jessica Lee ,  Christopher James Kelley ,  Alok Aggarwal ,  Harshit Kharbanda

IPC: G06V20/20 ,  G06T11/00 ,  G06V10/94 ,  G06F16/9535

CPC classification number: G06V20/20 ,  G06T11/00 ,  G06V10/945 ,  G06F16/9535 ,  G06T2200/24

Abstract: Systems and methods for providing scene understanding can include obtaining a plurality of images, stitching images associated with the scene, detecting objects in the scene, and providing information associated with the objects in the scene. The systems and methods can include determining filter tags or query tags that can be selected to filter the plurality of objects, which can then be provided as information to the user to provide further insight on the scene. The information may be provided in an augmented-reality experience via text or other user-interface elements anchored to objects in the images.

公开(公告)号：US20230259784A1

公开(公告)日：2023-08-17

申请号：US18140442

申请日：2023-04-27

Applicant: Google LLC

Inventor： Yanping Huang ,  Alok Aggarwal ,  Quoc V. Le ,  Esteban Alberto Real

IPC: G06N3/086 ,  G06N3/04

CPC classification number: G06N3/086 ,  G06N3/04

Abstract: A method for receiving training data for training a neural network (NN) to perform a machine learning (ML) task and for determining, using the training data, an optimized NN architecture for performing the ML task is described. Determining the optimized NN architecture includes: maintaining population data comprising, for each candidate architecture in a population of candidate architectures, (i) data defining the candidate architecture, and (ii) data specifying how recently a neural network having the candidate architecture has been trained while determining the optimized neural network architecture; and repeatedly performing multiple operations using each of a plurality of worker computing units to generate a new candidate architecture based on a selected candidate architecture having the best measure of fitness, adding the new candidate architecture to the population, and removing from the population the candidate architecture that was trained least recently.

公开(公告)号：US11669744B2

公开(公告)日：2023-06-06

申请号：US17475137

申请日：2021-09-14

Applicant: Google LLC

Inventor： Yanping Huang ,  Alok Aggarwal ,  Quoc V. Le ,  Esteban Alberto Real

IPC: G06N3/086 ,  G06N3/04

CPC classification number: G06N3/086 ,  G06N3/04

Abstract: A method for receiving training data for training a neural network (NN) to perform a machine learning (ML) task and for determining, using the training data, an optimized NN architecture for performing the ML task is described. Determining the optimized NN architecture includes: maintaining population data comprising, for each candidate architecture in a population of candidate architectures, (i) data defining the candidate architecture, and (ii) data specifying how recently a neural network having the candidate architecture has been trained while determining the optimized neural network architecture; and repeatedly performing multiple operations using each of a plurality of worker computing units to generate a new candidate architecture based on a selected candidate architecture having the best measure of fitness, adding the new candidate architecture to the population, and removing from the population the candidate architecture that was trained least recently.

公开(公告)号：US20220004879A1

公开(公告)日：2022-01-06

申请号：US17475137

申请日：2021-09-14

Applicant: Google LLC

Inventor： Yanping Huang ,  Alok Aggarwal ,  Quoc V. Le ,  Esteban Alberto Real

IPC: G06N3/08 ,  G06N3/04

Abstract: A method for receiving training data for training a neural network (NN) to perform a machine learning (ML) task and for determining, using the training data, an optimized NN architecture for performing the ML task is described. Determining the optimized NN architecture includes: maintaining population data comprising, for each candidate architecture in a population of candidate architectures, (i) data defining the candidate architecture, and (ii) data specifying how recently a neural network having the candidate architecture has been trained while determining the optimized neural network architecture; and repeatedly performing multiple operations using each of a plurality of worker computing units to generate a new candidate architecture based on a selected candidate architecture having the best measure of fitness, adding the new candidate architecture to the population, and removing from the population the candidate architecture that was trained least recently.

公开(公告)号：US20200320399A1

公开(公告)日：2020-10-08

申请号：US16906034

申请日：2020-06-19

Applicant: Google LLC

Inventor： Yanping Huang ,  Alok Aggarwal ,  Quoc V. Le ,  Esteban Alberto Real

IPC: G06N3/08 ,  G06N3/04

Abstract: A method for receiving training data for training a neural network (NN) to perform a machine learning (ML) task and for determining, using the training data, an optimized NN architecture for performing the ML task is described. Determining the optimized NN architecture includes: maintaining population data comprising, for each candidate architecture in a population of candidate architectures, (i) data defining the candidate architecture, and (ii) data specifying how recently a neural network having the candidate architecture has been trained while determining the optimized neural network architecture; and repeatedly performing multiple operations using each of a plurality of worker computing units to generate a new candidate architecture based on a selected candidate architecture having the best measure of fitness, adding the new candidate architecture to the population, and removing from the population the candidate architecture that was trained least recently.