-
公开(公告)号：US11599518B2
公开(公告)日：2023-03-07
申请号：US17147844
申请日：2021-01-13
Applicant: Google LLC
Inventor： Gaurav Menghani
IPC: G06F16/00 , G06F16/22 , G06F16/33 , G06F16/215 , G06F30/27 , G06N3/04 , G06N3/08 , G06F16/174 , H03M7/30
Abstract: The present disclosure provides systems, methods, and computer program products for providing efficient embedding table storage and lookup in machine-learning models. A computer-implemented method may include obtaining an embedding table comprising a plurality of embeddings respectively associated with a corresponding index of the embedding table, compressing each particular embedding of the embedding table individually allowing each respective embedding of the embedding table to be decompressed independent of any other embedding in the embedding table, packing the embedding table comprising individually compressed embeddings with a machine-learning model, receiving an input to use for locating an embedding in the embedding table, determining a lookup value based on the input to search indexes of the embedding table, locating the embedding based on searching the indexes of the embedding table for the determined lookup value, and decompressing the located embedding independent of any other embedding in the embedding table.
-
公开(公告)号：US20240211458A1
公开(公告)日：2024-06-27
申请号：US18390524
申请日：2023-12-20
Applicant: Google LLC
Inventor： Gaurav Menghani
IPC: G06F16/22 , G06F16/174 , G06F16/215 , G06F16/33 , G06F30/27 , G06N3/04 , G06N3/08 , H03M7/30
CPC classification number: G06F16/2282 , G06F16/215 , G06F16/2255 , G06F16/3347 , G06F30/27 , G06N3/04 , G06N3/08 , G06F16/1744 , G06F2211/007 , G06F2211/1014 , H03M7/30
Abstract: The present disclosure provides systems, methods, and computer program products for providing efficient embedding table storage and lookup in machine-learning models. A computer-implemented method may include obtaining an embedding table comprising a plurality of embeddings respectively associated with a corresponding index of the embedding table, compressing each particular embedding of the embedding table individually allowing each respective embedding of the embedding table to be decompressed independent of any other embedding in the embedding table, packing the embedding table comprising individually compressed embeddings with a machine-learning model, receiving an input to use for locating an embedding in the embedding table, determining a lookup value based on the input to search indexes of the embedding table, locating the embedding based on searching the indexes of the embedding table for the determined lookup value, and decompressing the located embedding independent of any other embedding in the embedding table.
-
公开(公告)号：US11410044B2
公开(公告)日：2022-08-09
申请号：US16605702
申请日：2018-05-21
Applicant: Google LLC
Inventor： Sujith Ravi , Gaurav Menghani , Prabhu Kaliamoorthi , Yicheng Fan
Abstract: The present disclosure provides an application development platform and associated software development kits (“SDKs”) that provide comprehensive services for generation, deployment, and management of machine-learned models used by computer applications such as, for example, mobile applications executed by a mobile computing device. In particular, the application development platform and SDKs can provide or otherwise leverage a unified, cross-platform application programming interface (“API”) that enables access to all of the different machine learning services needed for full machine learning functionality within the application. In such fashion, developers can have access to a single SDK for all machine learning services.
-
公开(公告)号：US20250063060A1
公开(公告)日：2025-02-20
申请号：US18450156
申请日：2023-08-15
Applicant: Google LLC
Inventor： Gaurav Menghani , Ariel Fuxman
Abstract: An example method can include obtaining, by a computing system, a first dataset including first reference inputs and first reference outputs. The example method can include training, by the computing system, a first machine-learned model using the first dataset. The example method can include obtaining, by the computing system, a second dataset including a plurality of second reference inputs, the plurality of second reference inputs obtained from a data corpus based on a distribution of second reference inputs in the second dataset. The example method can include processing, by the computing system and using the first machine-learned model, the plurality of second reference inputs to generate a plurality of second reference outputs corresponding to the plurality of second reference inputs. The example method can include training, by the computing system, a second machine-learned model using the plurality of second reference outputs and the plurality of second reference inputs.
-
Patent Agency Ranking
公开(公告)号：US20220222235A1
公开(公告)日：2022-07-14
申请号：US17147844
申请日：2021-01-13
Applicant: Google LLC
Inventor： Gaurav Menghani
IPC: G06F16/22 , G06F16/215 , G06N3/08 , G06N3/04
Abstract: The present disclosure provides systems, methods, and computer program products for providing efficient embedding table storage and lookup in machine-learning models. A computer-implemented method may include obtaining an embedding table comprising a plurality of embeddings respectively associated with a corresponding index of the embedding table, compressing each particular embedding of the embedding table individually allowing each respective embedding of the embedding table to be decompressed independent of any other embedding in the embedding table, packing the embedding table comprising individually compressed embeddings with a machine-learning model, receiving an input to use for locating an embedding in the embedding table, determining a lookup value based on the input to search indexes of the embedding table, locating the embedding based on searching the indexes of the embedding table for the determined lookup value, and decompressing the located embedding independent of any other embedding in the embedding table.
-
公开(公告)号：US12229108B2
公开(公告)日：2025-02-18
申请号：US18390524
申请日：2023-12-20
Applicant: Google LLC
Inventor： Gaurav Menghani
IPC: G06F16/00 , G06F16/215 , G06F16/22 , G06F30/27 , G06N3/04 , G06N3/08 , G06F16/174 , H03M7/30
Abstract: The present disclosure provides systems, methods, and computer program products for providing efficient embedding table storage and lookup in machine-learning models. A computer-implemented method may include obtaining an embedding table comprising a plurality of embeddings respectively associated with a corresponding index of the embedding table, compressing each particular embedding of the embedding table individually allowing each respective embedding of the embedding table to be decompressed independent of any other embedding in the embedding table, packing the embedding table comprising individually compressed embeddings with a machine-learning model, receiving an input to use for locating an embedding in the embedding table, determining a lookup value based on the input to search indexes of the embedding table, locating the embedding based on searching the indexes of the embedding table for the determined lookup value, and decompressing the located embedding independent of any other embedding in the embedding table.
-
公开(公告)号：US11892998B2
公开(公告)日：2024-02-06
申请号：US18161352
申请日：2023-01-30
Applicant: Google LLC
Inventor： Gaurav Menghani
IPC: G06F16/00 , G06F16/22 , G06F16/33 , G06F16/215 , G06F30/27 , G06N3/04 , G06N3/08 , G06F16/174 , H03M7/30
CPC classification number: G06F16/2282 , G06F16/215 , G06F16/2255 , G06F16/3347 , G06F30/27 , G06N3/04 , G06N3/08 , G06F16/1744 , G06F2211/007 , G06F2211/1014 , H03M7/30
Abstract: The present disclosure provides systems, methods, and computer program products for providing efficient embedding table storage and lookup in machine-learning models. A computer-implemented method may include obtaining an embedding table comprising a plurality of embeddings respectively associated with a corresponding index of the embedding table, compressing each particular embedding of the embedding table individually allowing each respective embedding of the embedding table to be decompressed independent of any other embedding in the embedding table, packing the embedding table comprising individually compressed embeddings with a machine-learning model, receiving an input to use for locating an embedding in the embedding table, determining a lookup value based on the input to search indexes of the embedding table, locating the embedding based on searching the indexes of the embedding table for the determined lookup value, and decompressing the located embedding independent of any other embedding in the embedding table.
-
公开(公告)号：US20230169058A1
公开(公告)日：2023-06-01
申请号：US18161352
申请日：2023-01-30
Applicant: Google LLC
Inventor： Gaurav Menghani
CPC classification number: G06F16/2282 , G06F16/3347 , G06F16/215 , G06F16/2255 , G06F30/27 , G06N3/04 , G06N3/08 , G06F16/1744
Abstract: The present disclosure provides systems, methods, and computer program products for providing efficient embedding table storage and lookup in machine-learning models. A computer-implemented method may include obtaining an embedding table comprising a plurality of embeddings respectively associated with a corresponding index of the embedding table, compressing each particular embedding of the embedding table individually allowing each respective embedding of the embedding table to be decompressed independent of any other embedding in the embedding table, packing the embedding table comprising individually compressed embeddings with a machine-learning model, receiving an input to use for locating an embedding in the embedding table, determining a lookup value based on the input to search indexes of the embedding table, locating the embedding based on searching the indexes of the embedding table for the determined lookup value, and decompressing the located embedding independent of any other embedding in the embedding table.
-
公开(公告)号：US20220374719A1
公开(公告)日：2022-11-24
申请号：US17861930
申请日：2022-07-11
Applicant: Google LLC
Inventor： Sujith Ravi , Gaurav Menghani , Prabhu Kaliamoorthi , Yicheng Fan
Abstract: The present disclosure provides an application development platform and associated software development kits (“SDKs”) that provide comprehensive services for generation, deployment, and management of machine-learned models used by computer applications such as, for example, mobile applications executed by a mobile computing device. In particular, the application development platform and SDKs can provide or otherwise leverage a unified, cross-platform application programming interface (“API”) that enables access to all of the different machine learning services needed for full machine learning functionality within the application. In such fashion, developers can have access to a single SDK for all machine learning services.
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.017 seconds)
