Google Inc.

Waymo LLC

Matthieu Devin

Jeffrey Adgate Dean

Kai Chen

Samy Bengio

Gregory Sean Corrado

Rajat Monga

Simon Tong

Uri N Lerner

Lawrence Jonathan Brunsman

Andrew Robert Kirmse

Tushar Udeshi

Vadim Furman

Pablo Bellver

James J Shuma

Aleksandra Faust

Yu-Hsin Chen

Franklin Morley

Carlos Alberto Fuertes Pascual

Andrew William Senior

Vincent Olivier Vanhoucke

Patrick An Phu Nguyen

Georg Heigold

Marc'aurelio Ranzato

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for correcting entity names. One method includes receiving texts and deriving a plurality of name-context pairs from the texts. The method further includes calculating a context consistency measure for each name-context pair and storing context-entity name data representing the name-context pairs. Another method includes identifying an entity name and one or more context terms from a query and generating candidate names for the entity name. The method further includes determining a score for each of the candidate names, selecting a number of top scoring candidate names, and using the selected candidate names to respond to the query.

Generating context-based spell corrections of entity names

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, systems, and apparatus, including computer programs encoded on computer storage media, for implementing an interactive autonomous vehicle agent. One of the methods includes receiving a request to generate an experience tuple for a vehicle in a particular driving context. A predicted environment observation representing a predicted environment of the autonomous vehicle after the candidate action is taken by the autonomous vehicle in an initial environment is generated, including providing an initial environment observation and the candidate action as input to a vehicle behavior model neural network trained to generate predicted environment observations. An immediate quality value is generated from a context-specific quality model that generates immediate quality values that are specific to the particular driving context. An experience tuple comprising the initial environment observation, the candidate action, and the immediate quality value is generated and used as input to a reinforcement learning system for the autonomous vehicle.

Interactive autonomous vehicle agent

Methods and systems for processing multilingual DNN acoustic models are described. An example method may include receiving training data that includes a respective training data set for each of two or more or languages. A multilingual deep neural network (DNN) acoustic model may be processed based on the training data. The multilingual DNN acoustic model may include a feedforward neural network having multiple layers of one or more nodes. Each node of a given layer may connect with a respective weight to each node of a subsequent layer, and the multiple layers of one or more nodes may include one or more shared hidden layers of nodes and a language-specific output layer of nodes corresponding to each of the two or more languages. Additionally, weights associated with the multiple layers of one or more nodes of the processed multilingual DNN acoustic model may be stored in a database.

Multilingual, acoustic deep neural networks

Embodiments relate to determining commute routes and clustering commute routes from a user's location history. Points in the user's location history may be clustered to find the user's home and work locations. Additionally, points along the user's commute may be identified to determine the user's typical commute. Similar commutes can be clustered together, and used to suggest various services to the user.

Extracting patterns from location history

Growing community of inventors

Los Altos Hills, CA, United States of America

Matthieu Devin