-
公开(公告)号：US10733535B1
公开(公告)日：2020-08-04
申请号：US15665236
申请日：2017-07-31
Applicant: Google LLC
Inventor： Gregory S. Corrado , Kai Chen , Jeffrey A. Dean , Samy Bengio , Rajat Monga , Matthieu Devin
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a model using parameter server shards. One of the methods includes receiving, at a parameter server shard configured to maintain values of a disjoint partition of the parameters of the model, a succession of respective requests for parameter values from each of a plurality of replicas of the model; in response to each request, downloading a current value of each requested parameter to the replica from which the request was received; receiving a succession of uploads, each upload including respective delta values for each of the parameters in the partition maintained by the shard; and updating values of the parameters in the partition maintained by the parameter server shard repeatedly based on the uploads of delta values to generate current parameter values.
-
公开(公告)号：US10241997B1
公开(公告)日：2019-03-26
申请号：US15682374
申请日：2017-08-21
Applicant: Google LLC
Inventor： Tomas Mikolov , Kai Chen , Gregory S. Corrado , Jeffrey A. Dean
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：US10127581B2
公开(公告)日：2018-11-13
申请号：US14733714
申请日：2015-06-08
Applicant: Google LLC
Inventor： Andrew E. Silverman , Kai Chen , Abhinay Sharma , Scott S. Benson , James A. Gallagher , Markus Mock , Bhavesh R. Mehta , Nicholas C. Fox , Angshuman Guha , Tomas Lloret Llinares
Abstract: An advertiser specifies a conversion-based bid for a conversion event associated with an ad. If a conversion event occurs for the ad, an effective conversion-based bid can be adjusted by a risk premium associated with the ad. An account associated with the advertiser can be debited based upon the adjusted effective conversion-based bid.
-
公开(公告)号：US12191007B2
公开(公告)日：2025-01-07
申请号：US16618656
申请日：2017-09-29
Applicant: Google LLC
Inventor： Kai Chen , Eyal Oren , Hector Yee , James Wilson , Alvin Rajkomar , Michaela Hardt
Abstract: Example embodiments relate to a method for training a predictive model from data. The method includes defining a multitude of predicates as binary functions operating on time sequences of the features or logical operations on the time sequences of the features. The method also includes iteratively training a boosting model by generating a number of new random predicates, scoring all the new random predicates by weighted information gain with respect to a class label associated with a prediction of the boosting model, selecting a number of the new random predicates with the highest weighted information gain and adding them to the boosting model, computing weights for all the predicates in the boosting model, removing one or more of the selected new predicates with the highest information gain from the boosting model in response to input from an operator. The method may include repeating the prior steps a plurality of times.
-
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.
-
Patent Agency Ranking
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：US20230402065A1
公开(公告)日：2023-12-14
申请号：US17835550
申请日：2022-06-08
Applicant: Google LLC
Inventor： Chenjie Gu , Wei-Hong Chuang , Min-Hsuan Tsai , Jianfeng Yang , Keren Gu-Lemberg , Flora Xue , Shubham Agrawal , Yuzhu Dong , Ji Zhang , Mahdis Mahdieh , Gagan Bansal , Kai Chen
IPC: G11B27/10 , G11B27/34 , G06F3/0481 , G06F3/04842
CPC classification number: G11B27/102 , G11B27/34 , G06F3/0481 , G06F3/04842
Abstract: Methods and systems for predicting titles for contents segments of media items at a platform using machine-learning are provided herein. A media item is provided to users of a platform, the media item having a plurality of content segments comprising a first content segment and a second content segment preceding the first content segment in the media item. The first content segment and a title of the second content segment are provided as input to a machine-learning model trained to predict a title for the first content segment that is consistent with the title of the second content segment. One or more outputs of the machine-learning model are obtained which indicate the title for the first content segment. An indication of each content segment and a respective title of each content segment are provided for presentation to at least one user of the one or more users.
-
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：US20230089961A1
公开(公告)日：2023-03-23
申请号：US18071308
申请日：2022-11-29
Applicant: Google LLC
Inventor： Scott Tadashi Davies , Kai Chen , Michael Jee-Kai Wang , Wei Jiang , Maryam Tavafi , Peter Zaimis Tipton
IPC: G06N20/00 , G06F16/22 , G06F16/435 , H04L67/01 , H04L67/06
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing content presentation. In one aspect, a system includes a training database that stores training data including attribute information about users and corresponding proxy metrics quantifying behavior by the users following content presentation; a content database; a model generator that accesses the training data and trains a model for content distribution; and a content distribution server that receives a content request, uses the model to select content, transmits data identifying the selected content, wherein the model: obtains a set of attributes for a user associated with the request, receives information about a given content, predicts a proxy metric based on the set of attributes and the information about the content, the predicted proxy metric providing information about subject retention or awareness; and identifies the given content for distribution if the predicted proxy metrics meet a threshold.
-
公开(公告)号：US11531925B2
公开(公告)日：2022-12-20
申请号：US15183335
申请日：2016-06-15
Applicant: Google LLC
Inventor： Scott Tadashi Davies , Kai Chen , Michael Jee-Kai Wang , Wei Jiang , Maryam Tavafi , Peter Zaimis Tipton
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for optimizing content presentation. In one aspect, a system includes a training database that stores training data including attribute information about users and corresponding proxy metrics quantifying behavior by the users following content presentation; a content database; a model generator that accesses the training data and trains a model for content distribution; and a content distribution server that receives a content request, uses the model to select content, transmits data identifying the selected content, wherein the model: obtains a set of attributes for a user associated with the request, receives information about a given content, predicts a proxy metric based on the set of attributes and the information about the content, the predicted proxy metric providing information about subject retention or awareness; and identifies the given content for distribution if the predicted proxy metrics meet a threshold.
-
-
-
-
-
-
-
-
-
Search Results
24
records
(took 0.022 seconds)
