Abstract: Disclosed in some examples, are methods, systems, devices, and machine-readable mediums that use one or more images (e.g., Quick-Response (QR) codes) displayed by a first application to both provide the location to obtain a second application and to copy a session from the first application to the second application once downloaded. In some examples, a session comprises an authentication session such that, when the session is copied, the user is logged into a network-based service within the second application with a same account as the user is already logged into with first application.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks. In one aspect, a system includes a neural network shrinking engine that is configured to receive a neural network being trained and generate a reduced neural network by a shrinking process. The shrinking process includes training the neural network based on a shrinking engine loss function that includes terms penalizing active neurons of the neural network and removing inactive neurons from the neural network. The system includes a neural network expansion engine that is configured to receive the neural network being trained and generate an expanded neural network by an expansion process including adding new neurons to the neural network and training the neural network based on an expanding engine loss function. The system includes a training subsystem that generates reduced neural networks and expanded neural networks.

Abstract: A device including a processor and a memory, in which the memory includes executable instructions for detecting that a first user has invited a second user to a communication session, wherein the first user is associated with a first user account registered to a first domain platform and the second user is not associated with any of user accounts registered to the first domain platform, the first domain platform defining a first user privilege granted to the user accounts registered to the first domain platform; causing a second user account associated with the second user to be created and registered to a second domain platform, the second domain platform being different from the first domain platform and defining a second user privilege granted to user accounts registered to the second domain platform; and granting the second user account the second user privilege.

Abstract: A device including a processor and a memory, in which the memory includes executable instructions for detecting that a first user has invited a second user to a communication session, wherein the first user is associated with a first user account registered to a first domain platform and the second user is not associated with any of user accounts registered to the first domain platform, the first domain platform defining a first user privilege granted to the user accounts registered to the first domain platform; causing a second user account associated with the second user to be created and registered to a second domain platform, the second domain platform being different from the first domain platform and defining a second user privilege granted to user accounts registered to the second domain platform; and granting the second user account the second user privilege.

Abstract: Disclosed in some examples, are methods, systems, devices, and machine-readable mediums that use one or more images (e.g., Quick-Response (QR) codes) displayed by a first application to both provide the location to obtain a second application and to copy a session from the first application to the second application once downloaded. In some examples, a session comprises an authentication session such that, when the session is copied, the user is logged into a network-based service within the second application with a same account as the user is already logged into with first application.

Abstract: A method includes receiving a first depth map that includes a plurality of first pixel depths and a second depth map that includes a plurality of second pixel depths. The first depth map corresponds to a reference depth scale and the second depth map corresponds to a relative depth scale. The method includes aligning the second pixel depths with the first pixel depths. The method includes transforming the aligned region of the second pixel depths such that transformed second edge pixel depths of the aligned region are coextensive with first edge pixel depths surrounding the corresponding region of the first pixel depths. The method includes generating a third depth map. The third depth map includes a first region corresponding to the first pixel depths and a second region corresponding to the transformed and aligned region of the second pixel depths.

Abstract: Techniques for managing an access privilege for users of an organization having first and second tenants includes storing, at a data storage, first user account data of a first user account associated with a first user of the first tenant, the first user account data including a first object identifier, a first tenant identifier and first access privilege information including access privileges granted to the first user account of the first tenant to access one or more resources; creating, for the first user associated with the first tenant, a second user account of the second tenant and second user account data of the second user account; setting the second user account data to include linked account information including the first object identifier and the first tenant identifier of the first user account data; and storing, at the data storage, the second user account data including the linked account information.

Abstract: Methods, systems, apparatuses, and computer program products are provided for automatically determining a home realm. An authentication request receiver interface may receive a request to access a resource and a device identifier from a client device. An authenticator may be enacted in response to receiving the request to access the resource that includes a home realm discoverer and an authentication user interface (UI) provider. The home realm discoverer may determine, based at least on the device identifier, the home realm from a plurality of realms. The authentication UI provider may provide, to the client device, an authentication UI via which a flat-name username can be submitted. Based at least on a flat-name user name and the determined home realm, access to the resource may be granted. In this manner, a user may input a flat-name username during sign-in, rather than inputting a realm or an entire e-mail address.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using consistency measures. One of the methods includes processing a particular training example from a mediator training data set using a first neural network to generate a first output for a first machine learning task; processing the particular training example in the mediator training data set using each of one or more second neural networks, wherein each second neural network is configured to generate a second output for a respective second machine learning task; determining, for each second machine learning task, a consistency target output for the first machine learning task; determining, for each second machine learning task, an error between the first output and the consistency target output corresponding to the second machine learning task; and generating a parameter update for the first neural network from the determined errors.

Abstract: A method includes receiving a first depth map that includes a plurality of first pixel depths and a second depth map that includes a plurality of second pixel depths. The first depth map corresponds to a reference depth scale and the second depth map corresponds to a relative depth scale. The method includes aligning the second pixel depths with the first pixel depths. The method includes transforming the aligned region of the second pixel depths such that transformed second edge pixel depths of the aligned region are coextensive with first edge pixel depths surrounding the corresponding region of the first pixel depths. The method includes generating a third depth map. The third depth map includes a first region corresponding to the first pixel depths and a second region corresponding to the transformed and aligned region of the second pixel depths.

Abstract: Techniques for managing access to content are provided that include receiving a first signal requesting an indication whether a user has an access privilege to access to a resource associated with a first tenant of an access management service or perform an operation by a data processing system using the resource, determining that a first user account associated with the user does not have an access privilege to access the resource; performing a nested access privilege check to determine whether the user is associated with a second user account that has the access privilege to access the resource; and granting via the communication network access to the resource responsive to the nested access privilege check determining that the user is associated with the second user account and the second user account is associated with the access privilege to access the resource.

Abstract: Methods for authentication session transfer using application download links are performed by systems and devices. A user or administrator at a first device enables the user to use an application at the user's mobile device. The user or administrator provides a request for the mobile application from the first device to an identity service. The identity service generates a uniform resource locator (URL) that encodes an authentication object generated by the identity service that is specific to the user's identity, and provides the URL to the mobile device. The identity service receives the authentication object back from a browser session of the URL at the user device, and establishes an authenticated browser session of the URL using the authentication object. The identity services authenticates the user's identity for the mobile application responsive to the mobile application invoking the authenticated browser session at the user device.

Abstract: A method includes receiving a first depth map that includes a plurality of first pixel depths and a second depth map that includes a plurality of second pixel depths. The first depth map corresponds to a reference depth scale and the second depth map corresponds to a relative depth scale. The method includes aligning the second pixel depths with the first pixel depths. The method includes transforming the aligned region of the second pixel depths such that transformed second edge pixel depths of the aligned region are coextensive with first edge pixel depths surrounding the corresponding region of the first pixel depths. The method includes generating a third depth map. The third depth map includes a first region corresponding to the first pixel depths and a second region corresponding to the transformed and aligned region of the second pixel depths.

Abstract: A device including a processor and a memory, in which the memory includes executable instructions for detecting that a first user has invited a second user to a communication session, wherein the first user is associated with a first user account registered to a first domain platform and the second user is not associated with any of user accounts registered to the first domain platform, the first domain platform defining a first user privilege granted to the user accounts registered to the first domain platform; causing a second user account associated with the second user to be created and registered to a second domain platform, the second domain platform being different from the first domain platform and defining a second user privilege granted to user accounts registered to the second domain platform; and granting the second user account the second user privilege.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks. In one aspect, a system includes a neural network shrinking engine that is configured to receive a neural network being trained and generate a reduced neural network by a shrinking process. The shrinking process includes training the neural network based on a shrinking engine loss function that includes terms penalizing active neurons of the neural network and removing inactive neurons from the neural network. The system includes a neural network expansion engine that is configured to receive the neural network being trained and generate an expanded neural network by an expansion process including adding new neurons to the neural network and training the neural network based on an expanding engine loss function. The system includes a training subsystem that generates reduced neural networks and expanded neural networks.

Abstract: A device including a processor and a memory, in which the memory includes executable instructions for detecting that a first user has invited a second user to a communication session, wherein the first user is associated with a first user account registered to a first domain platform and the second user is not associated with any of user accounts registered to the first domain platform, the first domain platform defining a first user privilege granted to the user accounts registered to the first domain platform; causing a second user account associated with the second user to be created and registered to a second domain platform, the second domain platform being different from the first domain platform and defining a second user privilege granted to user accounts registered to the second domain platform; and granting the second user account the second user privilege.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural networks. In one aspect, a system includes a neural network shrinking engine that is configured to receive a neural network being trained and generate a reduced neural network by a shrinking process. The shrinking process includes training the neural network based on a shrinking engine loss function that includes terms penalizing active neurons of the neural network and removing inactive neurons from the neural network. The system includes a neural network expansion engine that is configured to receive the neural network being trained and generate an expanded neural network by an expansion process including adding new neurons to the neural network and training the neural network based on an expanding engine loss function. The system includes a training subsystem that generates reduced neural networks and expanded neural networks.

Abstract: A MapReduce-based training framework exploits both data parallelism and model parallelism to scale training of complex models. Particular model architectures facilitate and benefit from use of such training framework. As one example, a machine-learned model can include a shared feature extraction portion configured to receive and process a data input to produce an intermediate feature representation and a plurality of prediction heads that are configured to receive and process the intermediate feature representation to respectively produce a plurality of predictions. For example, the data input can be a video and the plurality of predictions can be a plurality of classifications for content of the video (e.g., relative to a plurality of classes).

Abstract: A computer-implemented method for reducing the resource consumption of a convolutional neural network can include obtaining data descriptive of the convolutional neural network. The convolutional neural network can include a plurality of convolutional layers configured to perform convolutions using a plurality of kernels that each includes a plurality of kernel elements. The method can include training, for one or more training iterations, the convolutional neural network using a loss function that includes a group sparsifying regularizer term configured to sparsify a respective subset of the kernel elements of the kernel(s); following at least one training iteration, determining, for each of the kernel(s), whether to modify such kernel to remove the respective subset of the kernel elements based at least in part on respective values of the respective subset of kernel elements; and modifying at least one of the kernel(s) to remove the respective subset of the kernel elements.

Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a perspective computer vision model. The model is configured to receive input data characterizing an input scene in an environment from an input viewpoint and to process the input data in accordance with a set of model parameters to generate an output perspective representation of the scene from the input viewpoint. The system trains the model based on first data characterizing a scene in the environment from a first viewpoint and second data characterizing the scene in the environment from a second, different viewpoint.