公开(公告)号：US20170039483A1

公开(公告)日：2017-02-09

申请号：US14820751

申请日：2015-08-07

Applicant: Google Inc.

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

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

CPC classification number: G06N99/005 ,  G06F17/30477 ,  G06F17/30864 ,  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.

Abstract translation: 方法，系统和装置，包括在计算机存储介质上编码的计算机程序，用于训练因子分解模型以学习训练模型的模型输入的特征，使得因式分解模型预测机器学习模型被训练的结果。

公开(公告)号：US09269057B1

公开(公告)日：2016-02-23

申请号：US14102718

申请日：2013-12-11

Applicant: Google Inc.

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

IPC: G06N99/00

CPC classification number: G06N99/005 ,  G06F9/5066

Abstract: Systems and techniques are disclosed for generating weighted machine learned models using multi-shard combiners. A learner in a machine learning system may receive labeled positive and negative examples and workers within the learner may be configured to receive either positive or negative examples. A positive and negative statistic may be calculated for a given feature and may either be applied separately in a model or may be combined to generate an overall statistic.

Abstract translation: 公开了用于使用多分片组合器生成加权机器学习模型的系统和技术。 机器学习系统中的学习者可能会收到标签的正面和负面实例，学习者中的工作人员可能被配置为接受正面或者负面的例子。 可以为给定特征计算正和负统计量，并且可以在模型中单独应用，或者可以组合以产生总体统计量。

公开(公告)号：US20150317357A1

公开(公告)日：2015-11-05

申请号：US14268049

申请日：2014-05-02

Applicant: Google Inc.

Inventor： Jeremiah Harmsen ,  Tushar Deepak Chandra ,  Marcus Fontoura

IPC: G06F17/30 ,  G06N99/00

CPC classification number: G06F17/30424 ,  G06F17/30321 ,  G06F17/30622 ,  G06N5/025 ,  G06N99/005

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.

Abstract translation: 公开了用于基于由一个或多个机器学习模型生成的规则为可搜索索引生成条目的系统和技术。 索引条目可以包括与结果相关联的一个或多个令牌和结果概率。 可以基于事件的特征来识别令牌子集。 搜索索引可以根据事件搜索与令牌子集相似或匹配的令牌对应的结果及其各自的概率。