-
公开(公告)号：US10127475B1
公开(公告)日：2018-11-13
申请号：US15273572
申请日：2016-09-22
Applicant: Google LLC
Inventor： Gregory S. Corrado , Jeffrey A. Dean , Samy Bengio , Andrea L. Frome , Jonathon Shlens
IPC: G06K9/62
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying images. One of the methods includes obtaining data that associates each of a plurality of object category labels with a respective high-dimensional representation of the object category label, wherein the high-dimensional representation of the object category label is a numeric representation of the object category label in a high-dimensional space; receiving an input image; processing the input image using one or more core layers to generate an alternative representation of the input image; processing the alternative representation of the input image using a transformation layer to determine a high-dimensional representation for the input image; selecting, from the high-dimensional representations associated with the object category labels, a closest high-dimensional representation to the high-dimensional representation for the input image; and selecting the category label associated with the closest high-dimensional representation as a predicted label for the input image.
-
公开(公告)号：US20240211759A1
公开(公告)日：2024-06-27
申请号：US18596535
申请日：2024-03-05
Applicant: Google LLC
Inventor： Gregory S. Corrado , Kai Chen , Jeffrey A. Dean , Gary R. Holt , Julian P. Grady , Sharat Chikkerur , David W. Sculley, II
CPC classification number: G06N3/08 , G06F7/483 , G06F17/16 , G06N3/04 , G06N3/045 , G06N3/084 , G06F2207/483
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using embedded function with a deep network. One of the methods includes receiving an input comprising a plurality of features, wherein each of the features is of a different feature type; processing each of the features using a respective embedding function to generate one or more numeric values, wherein each of the embedding functions operates independently of each other embedding function, and wherein each of the embedding functions is used for features of a respective feature type; processing the numeric values using a deep network to generate a first alternative representation of the input, wherein the deep network is a machine learning model composed of a plurality of levels of non-linear operations; and processing the first alternative representation of the input using a logistic regression classifier to predict a label for the input.
-
公开(公告)号：US10679124B1
公开(公告)日：2020-06-09
申请号：US15368460
申请日：2016-12-02
Applicant: Google LLC
Inventor： Gregory S. Corrado , Kai Chen , Jeffrey A. Dean , Gary R. Holt , Julian P. Grady , Sharat Chikkerur , David W. Sculley, II
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using embedded function with a deep network. One of the methods includes receiving an input comprising a plurality of features, wherein each of the features is of a different feature type; processing each of the features using a respective embedding function to generate one or more numeric values, wherein each of the embedding functions operates independently of each other embedding function, and wherein each of the embedding functions is used for features of a respective feature type; processing the numeric values using a deep network to generate a first alternative representation of the input, wherein the deep network is a machine learning model composed of a plurality of levels of non-linear operations; and processing the first alternative representation of the input using a logistic regression classifier to predict a label for the input.
-
Patent Agency Ranking
公开(公告)号：US20180173722A1
公开(公告)日：2018-06-21
申请号：US15868928
申请日：2018-01-11
Applicant: Google LLC
Inventor： Jeffrey A. Dean , Sanjay Ghemawat , Andrew B. Fikes , Yasushi Saito
Abstract: A method of accessing data includes storing a table that includes a plurality of tablets corresponding to distinct non-overlapping table portions. Respective pluralities of tablet access objects and application objects are stored in a plurality of servers. A distinct application object and distinct tablet are associated with each tablet access object. Each application object corresponds to a distinct instantiation of an application associated with the table. The tablet access objects and associated application objects are redistributed among the servers in accordance with a first load-balancing criterion. A first request directed to a respective tablet is received from a client. In response, the tablet access object associated with the respective tablet is used to perform a data access operation on the respective tablet, and the application object associated with the respective tablet is used to perform an additional computational operation to produce a result to be returned to the client.
-
公开(公告)号：US11954597B2
公开(公告)日：2024-04-09
申请号：US17972466
申请日：2022-10-24
Applicant: Google LLC
Inventor： Gregory S. Corrado , Kai Chen , Jeffrey A. Dean , Gary R. Holt , Julian P. Grady , Sharat Chikkerur , David W. Sculley, II
CPC classification number: G06N3/08 , G06F7/483 , G06F17/16 , G06N3/04 , G06N3/045 , G06N3/084 , G06F2207/483
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using embedded function with a deep network. One of the methods includes receiving an input comprising a plurality of features, wherein each of the features is of a different feature type; processing each of the features using a respective embedding function to generate one or more numeric values, wherein each of the embedding functions operates independently of each other embedding function, and wherein each of the embedding functions is used for features of a respective feature type; processing the numeric values using a deep network to generate a first alternative representation of the input, wherein the deep network is a machine learning model composed of a plurality of levels of non-linear operations; and processing the first alternative representation of the input using a logistic regression classifier to predict a label for the input.
-
公开(公告)号：US20240070392A1
公开(公告)日：2024-02-29
申请号：US18503051
申请日：2023-11-06
Applicant: Google LLC
Inventor： Tomas Mikolov , Kai Chen , Gregory S. Corrado , Jeffrey A. Dean
IPC: G06F40/279 , G06F40/30 , G06N20/00 , G10L15/06
CPC classification number: G06F40/279 , G06F40/30 , G06N20/00 , G10L15/06
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.
-
公开(公告)号：US11809824B1
公开(公告)日：2023-11-07
申请号：US17175550
申请日：2021-02-12
Applicant: Google LLC
Inventor： Tomas Mikolov , Kai Chen , Gregory S. Corrado , Jeffrey A. Dean
IPC: G06F40/30 , G06F40/279 , G06N20/00 , G10L15/06
CPC classification number: G06F40/279 , G06F40/30 , G06N20/00 , G10L15/06
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing numeric representations of words. One of the methods includes obtaining a set of training data, wherein the set of training data comprises sequences of words; training a classifier and an embedding function on the set of training data, wherein training the embedding function comprises obtained trained values of the embedding function parameters; processing each word in the vocabulary using the embedding function in accordance with the trained values of the embedding function parameters to generate a respective numerical representation of each word in the vocabulary in the high-dimensional space; and associating each word in the vocabulary with the respective numeric representation of the word in the high-dimensional space.
-
公开(公告)号：US11481631B1
公开(公告)日：2022-10-25
申请号：US16895855
申请日：2020-06-08
Applicant: Google LLC
Inventor： Gregory S. Corrado , Kai Chen , Jeffrey A. Dean , Gary R. Holt , Julian P Grady , Sharat Chikkerur , David W. Sculley, II
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using embedded function with a deep network. One of the methods includes receiving an input comprising a plurality of features, wherein each of the features is of a different feature type; processing each of the features using a respective embedding function to generate one or more numeric values, wherein each of the embedding functions operates independently of each other embedding function, and wherein each of the embedding functions is used for features of a respective feature type; processing the numeric values using a deep network to generate a first alternative representation of the input, wherein the deep network is a machine learning model composed of a plurality of levels of non-linear operations; and processing the first alternative representation of the input using a logistic regression classifier to predict a label for the input.
-
-
-
-
-
-
-
Search Results
18
records
(took 0.013 seconds)
