公开(公告)号：US20200372359A1

公开(公告)日：2020-11-26

申请号：US16991258

申请日：2020-08-12

Applicant: Google LLC

Inventor： Tal Shaked ,  Rohan Anil ,  Hrishikesh Balkrishna Aradhye ,  Mustafa Ispir ,  Glen Anderson ,  Wei Chai ,  Mehmet Levent Koc ,  Jeremiah Joseph Harmsen ,  Xiaobing Liu ,  Gregory Sean Corrado ,  Tushar Deepak Chandra ,  Heng-Tze Cheng

IPC: G06N3/08 ,  G06N3/04

Abstract: A system includes one or more computers and one or more storage devices storing instructions that when executed by the one or more computers cause the computers to implement a combined machine learning model for processing an input including multiple features to generate a predicted output for the machine learning input. The combined model includes: a deep machine learning model configured to process the features to generate a deep model output; a wide machine learning model configured to process the features to generate a wide model output; and a combining layer configured to process the deep model output generated by the deep machine learning model and the wide model output generated by the wide machine learning model to generate the predicted output, in which the deep model and the wide model have been trained jointly on training data to generate the deep model output and the wide model output.

公开(公告)号：US10102482B2

公开(公告)日：2018-10-16

申请号：US14820751

申请日：2015-08-07

Applicant: Google LLC

Inventor： Heng-Tze Cheng ,  Jeremiah Harmsen ,  Alexandre Tachard Passos ,  David Edgar Lluncor ,  Shahar Jamshy ,  Tal Shaked ,  Tushar Deepak Chandra

IPC: G06N99/00 ,  G06F17/30 ,  G06N5/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a factorization model to learning features of model inputs of a trained model such that the factorization model is predictive of outcome for which the machine learned model is trained.

公开(公告)号：US10062035B1

公开(公告)日：2018-08-28

申请号：US14104004

申请日：2013-12-12

Applicant: Google LLC

Inventor： Tal Shaked ,  Tushar Deepak Chandra ,  Yoram Singer ,  Tze Way Eugene Ie ,  Joshua Redstone

IPC: G06F15/18 ,  G06N99/00 ,  G06F12/02

CPC classification number: G06N20/00

Abstract: The present disclosure provides methods and systems for using variable length representations of machine learning statistics. A method may include storing an n-bit representation of a first statistic at a first n-bit storage cell. A first update to the first statistic may be received, and it may be determined that the first update causes a first loss of precision of the first statistic as stored in the first n-bit storage cell. Accordingly, an m-bit representation of the first statistic may be stored at a first m-bit storage cell based on the determination. The first m-bit storage cell may be associated with the first n-bit storage cell. As a result, upon receiving an instruction to use the first statistic in a calculation, a combination of the n-bit representation and the m-bit representation may be used to perform the calculation.

公开(公告)号：US20210149890A1

公开(公告)日：2021-05-20

申请号：US17107790

申请日：2020-11-30

Applicant: Google LLC

Inventor： Jeremiah Harmsen ,  Tushar Deepak Chandra ,  Marcus Fontoura

IPC: G06F16/245 ,  G06N20/00 ,  G06F16/22 ,  G06N5/02 ,  G06F16/31

Abstract: Systems and techniques are disclosed for generating entries for a searchable index based on rules generated by one or more machine-learned models. The index entries can include one or more tokens correlated with an outcome and an outcome probability. A subset of tokens can be identified based on the characteristics of an event. The index may be searched for outcomes and their respective probabilities that correspond to tokens that are similar to or match the subset of tokens based on the event.

公开(公告)号：US10713585B2

公开(公告)日：2020-07-14

申请号：US14106900

申请日：2013-12-16

Applicant: Google LLC

Inventor： Tal Shaked ,  Tushar Deepak Chandra ,  James Vincent McFadden ,  Yoram Singer ,  Tze Way Eugene Ie

IPC: G06N20/00

Abstract: Systems and techniques are provided for template exploration in a large-scale machine learning system. A method may include obtaining multiple base templates, each base template comprising multiple features. A template performance score may be obtained for each base template and a first base template may be selected from among the multiple base templates based on the template performance score of the first base template. Multiple cross-templates may be constructed by generating a cross-template of the selected first base template and each of the multiple base templates. Performance of a machine learning model may be tested based on each cross-template to generate a cross-template performance score for each of the cross-templates. A first cross-template may be selected from among the multiple cross-templates based on the cross-template performance score of the cross-template. Accordingly, the first cross-template may be added to the machine learning model.