Here Global B.v.

Moritz Neun

Craig Barnes

Catalin Capota

Amir Jalalirad

Michael Kopp

Michael Sprague

Marco Scavuzzo

System and methods are provided for executing queries across multiple services and data sources using a Service Graph. The Service Graph is customizable and trainable using continuous feedback loops among the various components of the Service Graph. The Service Graph is configured to select at least one data source or at least one location service from a plurality heterogeneous data sources and location services, generate an execution strategy for searching the at least one location service or the at least one data source, and provide the results generated as a result of the execution strategy.

Service graph for location-based searching

Systems and methods are provided for training a machine learned model on a large number of devices, each device acquiring a local set of training data without sharing data sets across devices. The devices train the model on the respective device's set of training data. The devices communicate a parameter vector from the trained model asynchronously with a parameter server. The parameter server updates a master parameter vector and transmits the master parameter vector to the respective device.

Asynchronous parameter aggregation for machine learning

Growing community of inventors

Zurich, Switzerland

Moritz Neun