公开(公告)号：US12136026B2

公开(公告)日：2024-11-05

申请号：US18222649

申请日：2023-07-17

Applicant: Snap Inc.

Inventor： Yingzhen Yang ,  Jianchao Yang ,  Ning Xu

IPC: G06K9/00 ,  G06N3/04 ,  G06T5/20 ,  G06T7/10

Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

公开(公告)号：US12118464B2

公开(公告)日：2024-10-15

申请号：US17820657

申请日：2022-08-18

Applicant: Snap Inc.

Inventor： Lawrence Jason Muhlstein ,  Leonardo Ribas Machado das Neves ,  Yanen Li ,  Ning Xu

IPC: G06N3/08 ,  G06F3/0481 ,  G06F16/22 ,  G06F3/0488

CPC classification number: G06N3/08 ,  G06F3/0481 ,  G06F16/22 ,  G06F3/0488

Abstract: A neural network system can select content based on user and item content embeddings in an approach that can be updated in real time on the user device without server support. Requests for content sent to the server can include an anonymous user embedding that includes data describing the user's inputs. The content that is nearest to the user embedding in a joint embedding space can be returned as suggested content.

公开(公告)号：US11887357B2

公开(公告)日：2024-01-30

申请号：US17547548

申请日：2021-12-10

Applicant: Snap Inc.

Inventor： Jianchao Yang ,  Ning Xu ,  Jian Ren

IPC: G06K9/62 ,  G06V10/774 ,  G06F18/214 ,  G06F18/24 ,  G06F18/21 ,  G06F18/25 ,  G06V30/19 ,  G06V10/776 ,  G06V10/82 ,  H04L51/212

CPC classification number: G06V10/7753 ,  G06F18/217 ,  G06F18/2155 ,  G06F18/24 ,  G06F18/254 ,  G06V10/776 ,  G06V10/82 ,  G06V30/1916 ,  G06V30/19173 ,  H04L51/212

Abstract: Disclosed herein are arrangements that facilitate the transfer of knowledge from models for a source data-processing domain to models for a target data-processing domain. A convolutional neural network space for a source domain is factored into a first classification space and a first reconstruction space. The first classification space stores class information and the first reconstruction space stores domain-specific information. A convolutional neural network space for a target domain is factored into a second classification space and a second reconstruction space. The second classification space stores class information and the second reconstruction space stores domain-specific information. Distribution of the first classification space and the second classification space is aligned.

公开(公告)号：US11853399B2

公开(公告)日：2023-12-26

申请号：US18059928

申请日：2022-11-29

Applicant: Snap Inc.

Inventor： Jianfei Yu ,  Luis Carlos Dos Santos Marujo ,  Venkata Satya Pradeep Karuturi ,  Leonardo Ribas Machado das Neves ,  Ning Xu ,  William Brendel

IPC: G06F40/30 ,  G06F18/2431 ,  G06N3/08 ,  G06N20/20 ,  G06F40/284 ,  G06N3/045 ,  G10L25/30 ,  G06F40/295 ,  G06F40/279 ,  G06F40/289 ,  G10L15/18 ,  G10L15/06

CPC classification number: G06F18/2431 ,  G06F40/284 ,  G06F40/30 ,  G06N3/045 ,  G06N3/08 ,  G06N20/20 ,  G06F40/279 ,  G06F40/289 ,  G06F40/295 ,  G10L15/06 ,  G10L15/1807 ,  G10L15/1815 ,  G10L15/1822 ,  G10L25/30

Abstract: Sentiment classification can be implemented by an entity-level multimodal sentiment classification neural network. The neural network can include left, right, and target entity subnetworks. The neural network can further include an image network that generates representation data that is combined and weighted with data output by the left, right, and target entity subnetworks to output a sentiment classification for an entity included in a network post.

公开(公告)号：US20230359859A1

公开(公告)日：2023-11-09

申请号：US18222649

申请日：2023-07-17

Applicant: Snap Inc.

Inventor： Yingzhen Yang ,  Jianchao Yang ,  Ning Xu

IPC: G06N3/04 ,  G06T7/10 ,  G06T5/20

CPC classification number: G06N3/04 ,  G06T7/10 ,  G06T5/20

Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

公开(公告)号：US11763130B2

公开(公告)日：2023-09-19

申请号：US16949994

申请日：2020-11-23

Applicant: Snap Inc.

Inventor： Yingzhen Yang ,  Jianchao Yang ,  Ning Xu

IPC: G06K9/00 ,  G06N3/04 ,  G06T7/10 ,  G06T5/20

CPC classification number: G06N3/04 ,  G06T5/20 ,  G06T7/10

Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

公开(公告)号：US11637797B2

公开(公告)日：2023-04-25

申请号：US17397354

申请日：2021-08-09

Applicant: Snap Inc.

Inventor： Jianchao Yang ,  Yuke Zhu ,  Ning Xu ,  Kevin Dechau Tang ,  Jia Li

IPC: G06F15/16 ,  H04L51/10 ,  G06F16/22 ,  G06F16/51 ,  G06F16/583 ,  G06N20/00 ,  G06F16/9535 ,  G06F16/954 ,  G06F16/2457 ,  G06F16/951 ,  G06N3/04 ,  G06N3/08 ,  G06V20/00 ,  H04L51/52 ,  G06T7/00 ,  H04L67/01 ,  H04L67/55

Abstract: Systems, devices, methods, media, and instructions for automated image processing and content curation are described. In one embodiment a server computer system receives a content message from a first content source, and analyzes the content message to determine one or more quality scores and one or more content values associated with the content message. The server computer system analyzes the content message with a plurality of content collections of the database to identify a match between at least one of the one or more content values and a topic associated with at least a first content collection of the one or more content collections and automatically adds the content message to the first content collection based at least in part on the match. In various embodiments, different content values, image processing operations, and content selection operations are used to curate content collections.

公开(公告)号：US20230091110A1

公开(公告)日：2023-03-23

申请号：US17820657

申请日：2022-08-18

Applicant: Snap Inc.

Inventor： Lawrence Jason Muhlstein ,  Leonardo Ribas Machado das Neves ,  Yanen Li ,  Ning Xu

IPC: G06F16/22 ,  G06N3/08 ,  G06F3/0481

Abstract: A neural network system can select content based on user and item content embeddings in an approach that can be updated in real time on the user device without server support. Requests for content sent to the server can include an anonymous user embedding that includes data describing the user's inputs. The content that is nearest to the user embedding in a joint embedding space can be returned as suggested content.

公开(公告)号：US20230088029A1

公开(公告)日：2023-03-23

申请号：US18071865

申请日：2022-11-30

Applicant: Snap Inc.

Inventor： Jinxi Guo ,  Jia Li ,  Ning Xu

IPC: G10L25/30 ,  G06N3/04 ,  H04S7/00 ,  G06K9/62 ,  G06V20/00

Abstract: An acoustic environment identification system is disclosed that can use neural networks to accurately identify environments. The acoustic environment identification system can use one or more convolutional neural networks to generate audio feature data. A recursive neural network can process the audio feature data to generate characterization data. The characterization data can be modified using a weighting system that weights signature data items. Classification neural networks can be used to generate a classification of an environment.

公开(公告)号：US11315219B2

公开(公告)日：2022-04-26

申请号：US16888171

申请日：2020-05-29

Applicant: Snap Inc.

Inventor： Guohui Wang ,  Sumant Milind Hanumante ,  Ning Xu ,  Yuncheng Li

IPC: G06K9/62 ,  G06T3/40 ,  G06N3/08 ,  G06N3/04 ,  G06T1/20 ,  G06T11/60 ,  G06N3/063

Abstract: Remote distribution of multiple neural network models to various client devices over a network can be implemented by identifying a native neural network and remotely converting the native neural network to a target neural network based on a given client device operating environment. The native neural network can be configured for execution using efficient parameters, and the target neural network can use less efficient but more precise parameters.