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。