Google Inc.

Jeremiah Harmsen

Tushar Deepak Chandra

Tomasz J Tunguz-Zawislak

Mayur Dhondu Datar

Bahman Rabii

Julie Tung

Andres S Perez-Bergquist

Jason C Miller

Megan Nance

Marcus Felipe Fontoura

Tal Shaked

Mike Hochberg

Noah Fiedel

Heng-Tze Cheng

Terrence Rohan

Scott G Sheffer

Hrishikesh Balkrishna Aradhye

Gregory Sean Corrado

Tze Way Eugene Ie

Yoram Singer

Wei Chai

Christopher Olston

Glen Anderson

James McFadden

Mustafa Ispir

Sherry Qianhong Moore

Alexandre Tachard Passos

Michael Hochberg

Xiaobing Liu

Mehmet Levent Koc

Rohan Anil

Shahar Jamshy

David Edgar Lluncor

Kristen Riedt LeFevre

Mayur Datar

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.

Searchable index

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting a neural network with additional operations. One of the methods includes maintaining, by a computational graph system that manages execution of computational graphs representing neural network operations for users of the computational graph system, data specifying a plurality of pre-trained neural networks, wherein each of the pre-trained neural networks is a neural network that has been trained on training data to determine trained values of the respective parameters of the neural network; obtaining data specifying a user computational graph representing neural network operations, the user computational graph comprising a plurality of nodes connected by edges; identifying (i) an insertion point after a first node in the user computational graph and (ii) a particular pre-trained neural network from the plurality of pre-trained neural networks; and inserting a remote call node into the user computational graph.

Augmenting neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for batching inputs to machine learning models. One of the methods includes receiving a stream of requests, each request identifying a respective input for processing by a first machine learning model; adding the respective input from each request to a first queue of inputs for processing by the first machine learning model; determining, at a first time, that a count of inputs in the first queue as of the first time equals or exceeds a maximum batch size and, in response: generating a first batched input from the inputs in the queue as of the first time so that a count of inputs in the first batched input equals the maximum batch size, and providing the first batched input for processing by the first machine learning model.

Batching inputs to a machine learning model

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.

Wide and deep machine learning models

Structured data sets including one or more attributes are identified, each structured data set associated with, for example, a particular user. Values corresponding the at least one of the one or more attributes in each structured data set are identified. A condition established by a content provider, for instance, an advertiser, is compared to the identified values to determine if the condition is satisfied. When the condition is satisfied, one or more content items are identified to the users associated with the structured data sets containing identified values satisfying the condition.

User-targeted advertising

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.

Factorized models

Systems and techniques are disclosed for training a machine learning model based on one or more regularization penalties associated with one or more features. A template having a lower regularization penalty may be given preference over a template having a higher regularization penalty. A regularization penalty may be determined based on domain knowledge. A restrictive regularization penalty may be assigned to a template based on determining that a template occurrence is below a stability threshold and may be modified if the template occurrence meets or exceeds the stability threshold.

Template regularization for generalization of learning systems

A computer-implemented method for displaying advertisements to members of a network comprises identifying one or more communities of members, identifying one or more influencers in the one or more communities, and placing one or more advertisements at the profiles of one or more members in the identified one or more communities.

Network node ad targeting

Open profile data in a user profile, e.g., free-form fields in a user profile, are processed to identify interests and preferences of the user. The interests and preferences are utilized to identify categories associated with the user profile, and content items, e.g., advertisements, can be identified based on the categories.

Open profile content identification

A custodian profile, e.g., a user profile, associated with a first content item, e.g., an associated web page in a social network, can be identified as a first content item. The first content item can be utilized to identify one or more second content items, e.g., advertisements, that are displayed when the first content item is presented, e.g., viewed by another user of the social network.

Custodian based content identification

Growing community of inventors

San Jose, CA, United States of America

Jeremiah Harmsen