Google Inc.

International Business Machines Corporation

Gregory Sean Corrado

Jeffrey Adgate Dean

Kai Chen

Samy Bengio

Tomas Mikolov

Matthieu Devin

Rajat Monga

Quoc V Le

Ilya Sutskever

Jonathon Shlens

David W Sculley, Ii

Julian Paul Grady

Gary R Holt

Sharat Chikkerur

Kun Zhang

Phillip Neal Sharp

Prabhakar Raghavan

Balint Miklos

Thompson Alexander Ivor Gawley

Tobias Kaufmann

Karol Piotr Kurach

László Lukács

Andrea Lynn Frome

Andrew M Dai

Xiaobing Liu

Yi Zhang

James Wilson

Yingwei Cui

Bahman Rabii

Yoram Singer

Nissan Hajaj

Alvin Rishi Rajkomar

Xiaodan Song

Peter Junteng Liu

Benjamin Irvine

Eyal Oren

James Wexler

Patrik Sundberg

Hector Yee

Michaela Hardt

Xiaomi Sun

Jacob Marcus

Alexander Mossin

Dharmendra S Modha

Richard Carl Gossweiler, Iii

John Vernon Arthur

Paul A Merolla

Steven Kyle Esser

Hrishikesh Balkrishna Aradhye

Tushar Deepak Chandra

Tal Shaked

Mohammad Norouzi

Wei Chai

Jeremiah Harmsen

Glen Anderson

Arthur Asuncion

Mustafa Ispir

Richard Gossweiler

Marc'Aurelio Ranzato

Mehmet Levent Koc

Rohan Anil

Heng-Tze Cheng

Yong Sheng

Marc'aurelio Ranzato

Kurt Litsch

Gerardo Flores

Gavin Duggan

Johannes Christian Schuler

Iiya Sutskever

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.

Computing numeric representations of words in a high-dimensional space

Methods and apparatus related to determining reply content for a reply to an electronic communication. Some implementations are directed generally toward analyzing a corpus of electronic communications to determine relationships between one or more original message features of 'original' messages of electronic communications and reply content that is included in “reply” messages of those electronic communications. Some implementations are directed generally toward providing reply text to include in a reply to a communication based on determined relationships between one or more message features of the communication and the reply text.

Determining reply content for a reply to an electronic communication

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting likelihoods of conditions being satisfied using recurrent neural networks. One of the systems is configured to process a temporal sequence comprising a respective input at each of a plurality of time steps and comprises: one or more recurrent neural network layers; one or more logistic regression nodes, wherein each of the logistic regression nodes corresponds to a respective condition from a predetermined set of conditions, and wherein each of the logistic regression nodes is configured to, for each of the plurality of time steps: receive the network internal state for the time step; and process the network internal state for the time step in accordance with current values of a set of parameters of the logistic regression node to generate a future condition score for the corresponding condition for the time step.

Predicting likelihoods of conditions being satisfied using neural networks

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for classifying data objects. One of the methods includes obtaining data that associates each term in a vocabulary of terms with a respective high-dimensional representation of the term; obtaining classification data for a data object, wherein the classification data includes a respective score for each of a plurality of categories, and wherein each of the categories is associated with a respective category label; computing an aggregate high-dimensional representation for the data object from high-dimensional representations for the category labels associated with the categories and the respective scores; identifying a first term in the vocabulary of terms having a high-dimensional representation that is closest to the aggregate high-dimensional representation; and selecting the first term as a category label for the data object.

Classifying data objects

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.

Using embedding functions with a deep network

A system for predicting and summarizing medical events from electronic health records includes a computer memory storing aggregated electronic health records from a multitude of patients of diverse age, health conditions, and demographics including medications, laboratory values, diagnoses, vital signs, and medical notes. The aggregated electronic health records are converted into a single standardized data structure format and ordered arrangement per patient, e.g., into a chronological order. A computer (or computer system) executes one or more deep learning models trained on the aggregated health records to predict one or more future clinical events and summarize pertinent past medical events related to the predicted events on an input electronic health record of a patient having the standardized data structure format and ordered into a chronological order. An electronic device configured with a healthcare provider-facing interface displays the predicted one or more future clinical events and the pertinent past medical events of the patient.

System and method for predicting and summarizing medical events from electronic health records

Predicting likelihoods of conditions being satisfied using recurrent neural networks

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.

Training a model using parameter server shards

Methods and apparatus related to determining reply content for a reply to an electronic communication. Some implementations are directed generally toward analyzing a corpus of electronic communications to determine relationships between one or more original message features of 'original' messages of electronic communications and reply content that is included in 'reply' messages of those electronic communications. Some implementations are directed generally toward providing reply text to include in a reply to a communication based on determined relationships between one or more message features of the communication and the reply text.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating document vector representations. One of the methods includes obtaining a new document; selecting a plurality of new document word sets; and determining a vector representation for the new document using a trained neural network system, wherein the trained neural network system comprises: a document embedding layer and a classifier, and wherein determining the vector representation for the new document using the trained neural network system comprises iteratively providing each of the plurality of new document word sets to the trained neural network system to determine the vector representation for the new document using gradient descent.

Generating vector representations of documents

Growing community of inventors

Mountain View, CA, United States of America

Gregory Sean Corrado