-
公开(公告)号:US10430464B1
公开(公告)日:2019-10-01
申请号:US15849880
申请日:2017-12-21
Applicant: GOOGLE LLC
Inventor: Sujith Ravi , Qiming Diao
IPC: G06F17/30 , G06F16/901 , G06N20/00
Abstract: Systems and methods for adding labels to a graph are disclosed. One system includes a plurality of computing devices including processors and memory storing an input graph generated based on a source data set, where an edge represents a similarity measure between two nodes in the input graph, the input graph being distributed across the plurality of computing devices, and some of the nodes are seed nodes associated with one or more training labels from a set of labels, each training label having an associated original weight. The memory may also store instructions that, when executed by the processors, cause the plurality of distributed computing devices to propagate the training labels through the input graph using a sparsity approximation for label propagation, resulting in learned weights for respective node and label pairs, and automatically update the source data set using node and label pairs selected based on the learned weights.
-
公开(公告)号:US10248889B2
公开(公告)日:2019-04-02
申请号:US15839739
申请日:2017-12-12
Applicant: Google LLC
Inventor: Robin Dua , Sujith Ravi
Abstract: A method includes identifying images associated with a user, where the image is identified as at least one of captured by a user device associated with the user, stored on the user device associated with the user, and stored in cloud storage associated with the user. The method also includes for each of the images, determining one or more labels, wherein the one or more labels are based on at least one of metadata and a primary annotation. The method also includes generating a mapping of the one or more labels to one or more confidence scores, wherein the one or more confidence scores indicate an extent to which the one or more labels apply to corresponding images. The method also includes interacting with the user to obtain identifying information that is used to categorize one or more of the images.
-
公开(公告)号:US11586927B2
公开(公告)日:2023-02-21
申请号:US16265793
申请日:2019-02-01
Applicant: Google LLC
Inventor: Zhen Li , Yi-ting Chen , Yaxi Gao , Da-Cheng Juan , Aleksei Timofeev , Chun-Ta Lu , Futang Peng , Sujith Ravi , Andrew Tomkins , Thomas J. Duerig
IPC: G06K9/00 , G06N3/084 , G06F16/538 , G06F16/9538 , G06K9/62 , G06N3/04
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.
-
公开(公告)号:US11423233B2
公开(公告)日:2022-08-23
申请号:US17141473
申请日:2021-01-05
Applicant: Google LLC
Inventor: Sujith Ravi , Zornitsa Kozareva
IPC: G06F40/30 , G06N3/08 , G06N3/04 , G06F40/253
Abstract: The present disclosure provides projection neural networks and example applications thereof. In particular, the present disclosure provides a number of different architectures for projection neural networks, including two example architectures which can be referred to as: Self-Governing Neural Networks (SGNNs) and Projection Sequence Networks (ProSeqoNets). Each projection neural network can include one or more projection layers that project an input into a different space. For example, each projection layer can use a set of projection functions to project the input into a bit-space, thereby greatly reducing the dimensionality of the input and enabling computation with lower resource usage. As such, the projection neural networks provided herein are highly useful for on-device inference in resource-constrained devices. For example, the provided SGNN and ProSeqoNet architectures are particularly beneficial for on-device inference such as, for example, solving natural language understanding tasks on-device.
-
公开(公告)号:US20210124878A1
公开(公告)日:2021-04-29
申请号:US17141473
申请日:2021-01-05
Applicant: Google LLC
Inventor: Sujith Ravi , Zornitsa Kozareva
IPC: G06F40/30 , G06N3/08 , G06N3/04 , G06F40/253
Abstract: The present disclosure provides projection neural networks and example applications thereof. In particular, the present disclosure provides a number of different architectures for projection neural networks, including two example architectures which can be referred to as: Self-Governing Neural Networks (SGNNs) and Projection Sequence Networks (ProSegoNets). Each projection neural network can include one or more projection layers that project an input into a different space. For example, each projection layer can use a set of projection functions to project the input into a bit-space, thereby greatly reducing the dimensionality of the input and enabling computation with lower resource usage. As such, the projection neural networks provided herein are highly useful for on-device inference in resource-constrained devices. For example, the provided SGNN and ProSegoNet architectures are particularly beneficial for on-device inference such as, for example, solving natural language understanding tasks on-device.
-
公开(公告)号:US20210049165A1
公开(公告)日:2021-02-18
申请号:US17086564
申请日:2020-11-02
Applicant: Google LLC
Inventor: Marc Alexander Najork , Sujith Ravi , Michael Bendersky , Peter Shao-sen Young , Timothy Youngjin Sohn , Mingyang Zhang , Thomas Nelson , Xuanhui Wang
IPC: G06F16/248 , G06F16/2455 , G06F16/951 , G06F16/38
Abstract: Methods, systems, apparatus, including computer programs encoded on computer storage medium, to facilitate identification of additional trigger-terms for a structured information card. In one aspect, the method includes actions of accessing data associated with a template for presenting structured information, wherein the accessed data references (i) a label term and (ii) a value. Other actions may include obtaining a candidate label term, identifying one or more entities that are associated with the label term, identifying one or more of the entities that are associated with the candidate label term, and for each particular entity of the one or more entities that are associated with the candidate label term, associating, with the candidate label term, (i) a label term that is associated with the particular entity, and (ii) the value associated with the label term.
-
公开(公告)号:US10862836B2
公开(公告)日:2020-12-08
申请号:US16560815
申请日:2019-09-04
Applicant: Google LLC
Inventor: John Patrick McGregor, Jr. , Ryan Cassidy , Ariel Fuxman , Vivek Ramavajjala , Sujith Ravi , Sergey Nazarov , Amit Fulay
IPC: H04L12/58 , G06K9/72 , G06K9/62 , G06F3/0484
Abstract: Implementations relate to automatic response suggestions based on images received in messaging applications. In some implementations, a computer-executed method includes detecting a first image included within a first message received at a second device over a communication network from a first device of a first user, and programmatically analyzing the first image to extract a first image content. The method includes retrieving a first semantic concept associated with the first image content, programmatically generating a suggested response to the first message based on the first semantic concept, and transmitting instructions causing rendering of the suggested response in the messaging application as a suggestion to a second user of the second device.
-
公开(公告)号:US20200250537A1
公开(公告)日:2020-08-06
申请号:US16265793
申请日:2019-02-01
Applicant: Google LLC
Inventor: Zhen Li , Yi-ting Chen , Yaxi Gao , Da-Cheng Juan , Aleksei Timofeev , Chun-Ta Lu , Futang Peng , Sujith Ravi , Andrew Tomkins , Thomas J. Duerig
IPC: G06N3/08 , G06K9/62 , G06F16/9538 , G06F16/538 , G06N3/04
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training an image embedding model. In one aspect, a method comprises: obtaining training data comprising a plurality of training examples, wherein each training example comprises: an image pair comprising a first image and a second image; and selection data indicating one or more of: (i) a co-click rate of the image pair, and (ii) a similar-image click rate of the image pair; and using the training data to train an image embedding model having a plurality of image embedding model parameters.
-
公开(公告)号:US20200042596A1
公开(公告)日:2020-02-06
申请号:US16135545
申请日:2018-09-19
Applicant: Google LLC
Inventor: Sujith Ravi , Zornitsa Kozareva
Abstract: The present disclosure provides projection neural networks and example applications thereof. In particular, the present disclosure provides a number of different architectures for projection neural networks, including two example architectures which can be referred to as: Self-Governing Neural Networks (SGNNs) and Projection Sequence Networks (ProSeqoNets). Each projection neural network can include one or more projection layers that project an input into a different space. For example, each projection layer can use a set of projection functions to project the input into a bit-space, thereby greatly reducing the dimensionality of the input and enabling computation with lower resource usage. As such, the projection neural networks provided herein are highly useful for on-device inference in resource-constrained devices. For example, the provided SGNN and ProSeqoNet architectures are particularly beneficial for on-device inference such as, for example, solving natural language understanding tasks on-device.
-
公开(公告)号:US12112134B2
公开(公告)日:2024-10-08
申请号:US17582206
申请日:2022-01-24
Applicant: Google LLC
Inventor: Dana Movshovitz-Attias , John Patrick McGregor, Jr. , Gaurav Nemade , Sujith Ravi , Jeongwoo Ko , Dora Demszky
IPC: G06F40/289 , G06F40/30 , G06N20/00
CPC classification number: G06F40/289 , G06F40/30 , G06N20/00
Abstract: The technology relates to methods for detecting and classifying emotions in textual communication, and using this information to suggest graphical indicia such as emoji, stickers or GIFs to a user. Two main types of models are fully supervised models and few-shot models. In addition to fully supervised and few-shot models, other types of models focusing on the back-end (server) side or client (on-device) side may also be employed. Server-side models are larger-scale models that can enable higher degrees of accuracy, such as for use cases where models can be hosted on cloud servers where computational and storage resources are relatively abundant. On-device models are smaller-scale models, which enable use on resource-constrained devices such as mobile phones, smart watches or other wearables (e.g., head mounted displays), in-home devices, embedded devices, etc.
-
-
-
-
-
-
-
-
-