公开(公告)号：US20240169221A1

公开(公告)日：2024-05-23

申请号：US18426325

申请日：2024-01-29

Applicant: GOOGLE LLC

Inventor： Daniel M. Keysers ,  Victor Carbune ,  Thomas Deselaers

IPC: G06N5/04 ,  G06N20/00

CPC classification number: G06N5/04 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing actionable suggestions are disclosed. In one aspect, a method includes receiving (i) an indication that an event detection module has determined that a shared event of a particular type is presently occurring or has occurred, and (ii) data referencing an attribute associated with the shared event. The method includes selecting, from among multiple output templates that are each associated with a different type of shared event, a particular output template associated with the particular type of shared event detected by the module. The method generates a notification for output using at least (i) the selected particular output template, and (ii) the data referencing the attribute associated with the shared event. The method then provides, for output to a user device, the notification that is generated.

公开(公告)号：US10185872B2

公开(公告)日：2019-01-22

申请号：US14967901

申请日：2015-12-14

Applicant: Google LLC

Inventor： Daniel M. Keysers ,  Thomas Deselaers ,  Henry Allan Rowley

IPC: G06K9/00 ,  G06K9/52

Abstract: An optimal recognition for handwritten input based on receiving a touch input from a user may be selected by applying both a delayed stroke recognizer as well as an overlapping recognizer to the handwritten input. A score may be generated for both the delayed stroke recognition as well as the overlapping recognition and the recognition corresponding to the highest score may be presented as the overall recognition.

公开(公告)号：US12079954B2

公开(公告)日：2024-09-03

申请号：US17603362

申请日：2019-06-10

Applicant: Google LLC

Inventor： Victor Carbune ,  Daniel M. Keysers ,  Thomas Deselaers

IPC: G06K9/40 ,  G06T3/4046 ,  G06T5/00 ,  G06T5/50

CPC classification number: G06T3/4046 ,  G06T5/50 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that use generative adversarial models to increase the quality of sensor data generated by a first environmental sensor to resemble the quality of sensor data generated by another sensor having a higher quality than the first environmental sensor. A set of first and second training data generated by a first environmental sensor having a first quality and a second sensor having a target quality, respectively, is received. A generative adversarial mode is trained, using the set of first training data and the set of second training data, to modify sensor data from the first environmental sensor by reducing a difference in quality between the sensor data generated by the first environmental sensor and sensor data generated by the target environmental sensor.

公开(公告)号：US20210073663A1

公开(公告)日：2021-03-11

申请号：US17102108

申请日：2020-11-23

Applicant: Google LLC

Inventor： Daniel M. Keysers ,  Victor Carbune ,  Thomas Deselaers

IPC: G06N5/04 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing actionable suggestions are disclosed. In one aspect, a method includes receiving (i) an indication that an event detection module has determined that a shared event of a particular type is presently occurring or has occurred, and (ii) data referencing an attribute associated with the shared event. The method includes selecting, from among multiple output templates that are each associated with a different type of shared event, a particular output template associated with the particular type of shared event detected by the module. The method generates a notification for output using at least (i) the selected particular output template, and (ii) the data referencing the attribute associated with the shared event. The method then provides, for output to a user device, the notification that is generated.

公开(公告)号：US20220108171A1

公开(公告)日：2022-04-07

申请号：US17488166

申请日：2021-09-28

Applicant: Google LLC

Inventor： Joan Puigcerver i Perez ,  Basil Mustafa ,  André Susano Pinto ,  Carlos Riquelme Ruiz ,  Neil Matthew Tinmouth Houlsby ,  Daniel M. Keysers

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training neural networks using transfer learning. One of the methods includes training a neural network to perform a first prediction task, including: obtaining trained model parameters for each of a plurality of candidate neural networks, wherein each candidate neural network has been pre-trained to perform a respective second prediction task that is different from the first prediction task; obtaining a plurality of training examples corresponding to the first prediction task; selecting a proper subset of the plurality of candidate neural networks using the plurality of training examples; generating, for each candidate neural network, one or more fine-tuned neural networks, wherein each fine-tuned neural network is generated by updating the model parameters of the candidate neural network using the plurality of training examples; and determining model parameters for the neural network using the respective fine-tuned neural networks.

公开(公告)号：US10397163B2

公开(公告)日：2019-08-27

申请号：US15345328

申请日：2016-11-07

Applicant: Google LLC

Inventor： Victor Carbune ,  Thomas Deselaers ,  Daniel M. Keysers

IPC: G06F15/16 ,  H04L12/58 ,  H04L29/08 ,  G06Q50/00 ,  G16H20/30

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer-readable storage medium for implementing one or more application programming interfaces (APIs) that configure applications stored in an electronic device are described. An application may be configured to receive event information from various sources based on user preferences and application permissions. In response to receiving the event information, the app may determine whether a notification should be issued to a user. This determination may be made based on various factors such as the type of event, user history, contextual data, ranking data, and application permissions. The notifications may include one or more of messages to the user and recommended actions for consideration by the user. The actions may include sharing data with other users who share a presence or interest in an event with the user.

公开(公告)号：US11887016B2

公开(公告)日：2024-01-30

申请号：US17102108

申请日：2020-11-23

Applicant: Google LLC

Inventor： Daniel M. Keysers ,  Victor Carbune ,  Thomas Deselaers

IPC: G06N5/04 ,  G06N20/00

CPC classification number: G06N5/04 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing actionable suggestions are disclosed. In one aspect, a method includes receiving (i) an indication that an event detection module has determined that a shared event of a particular type is presently occurring or has occurred, and (ii) data referencing an attribute associated with the shared event. The method includes selecting, from among multiple output templates that are each associated with a different type of shared event, a particular output template associated with the particular type of shared event detected by the module. The method generates a notification for output using at least (i) the selected particular output template, and (ii) the data referencing the attribute associated with the shared event. The method then provides, for output to a user device, the notification that is generated.

公开(公告)号：US20220375211A1

公开(公告)日：2022-11-24

申请号：US17737507

申请日：2022-05-05

Applicant: Google LLC

Inventor： Ilya Tolstikhin ,  Neil Matthew Tinmouth Houlsby ,  Alexander Kolesnikov ,  Lucas Klaus Beyer ,  Alexey Dosovitskiy ,  Mario Lucic ,  Xiaohua Zhai ,  Thomas Unterthiner ,  Daniel M. Keysers ,  Jakob D. Uszkoreit ,  Yin Ching Jessica Yung ,  Andreas Steiner

IPC: G06V10/82 ,  G06V10/764 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using mixer 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 mixer neural network layers.

公开(公告)号：US20220253694A1

公开(公告)日：2022-08-11

申请号：US17560118

申请日：2021-12-22

Applicant: Google LLC

Inventor： Ibrahim Alabdulmohsin ,  Hartmut Maennel ,  Daniel M. Keysers

IPC: G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using re-initialization. One of the methods includes, at each time step in a sequence of time steps: identifying current values of the weights as of the training time step; selecting one of the layer blocks; generating new values for the weights of the plurality of neural network layers, comprising: re-initializing the values of the weights of at least the neural network layers in the layer blocks that are after the selected layer block without re-initializing the current values of the weights of the neural network layers in the layer block and the neural network layers in any layer block that is before the selected layer block; and raining the neural network starting from the new values for the weights of the plurality of neural network layers.

公开(公告)号：US20220198609A1

公开(公告)日：2022-06-23

申请号：US17603362

申请日：2019-06-10

Applicant: Daniel M. KEYSERS ,  Thomas DESELAERS ,  Victor CARBUNE ,  Google LLC

Inventor： Victor Carbune ,  Daniel M. Keysers ,  Thomas Deselaers

IPC: G06T3/40 ,  G06T5/50

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, that use generative adversarial models to increase the quality of sensor data generated by a first environmental sensor to resemble the quality of sensor data generated by another sensor having a higher quality than the first environmental sensor. A set of first and second training data generated by a first environmental sensor having a first quality and a second sensor having a target quality, respectively, is received. A generative adversarial mode is trained, using the set of first training data and the set of second training data, to modify sensor data from the first environmental sensor by reducing a difference in quality between the sensor data generated by the first environmental sensor and sensor data generated by the target environmental sensor.