公开(公告)号：US10885277B2

公开(公告)日：2021-01-05

申请号：US16135545

申请日：2018-09-19

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：US20200349450A1

公开(公告)日：2020-11-05

申请号：US16926908

申请日：2020-07-13

Applicant: Google LLC

Inventor： Sujith Ravi

IPC: G06N3/10 ,  G06F17/16 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a projection neural network. In one aspect, a projection neural network is configured to receive a projection network input and to generate a projection network output from the projection network input. The projection neural network includes a sequence of one or more projection layers. Each projection layer has multiple projection layer parameters, and is configured to receive a layer input, apply multiple projection layer functions to the layer input, and generate a layer output by applying the projection layer parameters for the projection layer to the projection function outputs.

公开(公告)号：US10748066B2

公开(公告)日：2020-08-18

申请号：US15983441

申请日：2018-05-18

Applicant: Google LLC

Inventor： Sujith Ravi

IPC: G06N3/10 ,  G06F17/16 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for a projection neural network. In one aspect, a projection neural network is configured to receive a projection network input and to generate a projection network output from the projection network input. The projection neural network includes a sequence of one or more projection layers. Each projection layer has multiple projection layer parameters, and is configured to receive a layer input, apply multiple projection layer functions to the layer input, and generate a layer output by applying the projection layer parameters for the projection layer to the projection function outputs.

公开(公告)号：US10412030B2

公开(公告)日：2019-09-10

申请号：US16003661

申请日：2018-06-08

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：US10015124B2

公开(公告)日：2018-07-03

申请号：US15709418

申请日：2017-09-19

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

CPC classification number: H04L51/10 ,  G06F3/04842 ,  G06K9/6202 ,  G06K9/6215 ,  G06K9/726 ,  H04L51/02 ,  H04L51/32

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.