Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.

Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.

Abstract: The technology described herein builds an optimal refresh schedule by minimizing a cost function constrained by an available refresh bandwidth. The cost function receives an importance score for a content item and a change rate for the content item as input in order to optimize the schedule. The cost function is considered optimized when a refresh schedule is found that minimizes the cost while using the available bandwidth and no more. The technology can build an optimized schedule to refresh content with incomplete change data, content with complete change data, or a mixture of content with and without complete change data. It can also re-learn content item change rates from its own schedule execution history and re-compute the refresh schedule, ensuring that this schedule takes into account the latest trends in content item updates.

Abstract: The technology described herein builds an optimal refresh schedule by minimizing a cost function constrained by an available refresh bandwidth. The cost function receives an importance score for a content item and a change rate for the content item as input in order to optimize the schedule. The cost function is considered optimized when a refresh schedule is found that minimizes the cost while using the available bandwidth and no more. The technology can build an optimized schedule to refresh content with incomplete change data, content with complete change data, or a mixture of content with and without complete change data. It can also re-learn content item change rates from its own schedule execution history and re-compute the refresh schedule, ensuring that this schedule takes into account the latest trends in content item updates.

Abstract: The subject disclosure is directed towards processing evidence, which may include high-dimensional streaming evidence, into a future belief state. The existing evidence is used to project a belief about a future state. The future belief state may be used to determine whether to wait for additional evidence, or to act now without waiting for additional evidence, e.g., based on a cost of the delay. For example, an autonomous assistant may decide based upon the belief whether to engage a person or not, or to wait for more information before the engagement decision is made.

Abstract: A system is described for integrating a search engine and one or more social network resources. The system operates by determining whether a search operation being conducted by a user warrants interaction with a social network resource. If so, the system may provide an invitation to the user to forward a query-related message to the social network resource. The system then sends the message to a group of contacts via the social network resource, where the group of contacts can be defined in various ways. The system receives a response from at least one contact in the group of contacts and presents that response to the user using various delivery mechanisms, as governed by various delivery timings.

Abstract: Systems and methods to determine when a media is a high-fidelity reproduction of an original media from a trusted entity are disclosed. In certain aspects, systems and method for generating a fragile watermark are disclosed. The fragile watermark may be inserted into digital media in a manner such that the watermark cannot be identified if the media content is significantly altered. Media content may be subsequently analyzed to determine the presence of a fragile watermark. When the fragile watermark is present, provenance of the media content can be verified and an indication of provenance is provided to the user.

Abstract: The technology described herein builds an optimal refresh schedule by minimizing a cost function constrained by an available refresh bandwidth. The cost function receives an importance score for a content item and a change rate for the content item as input in order to optimize the schedule. The cost function is considered optimized when a refresh schedule is found that minimizes the cost while using the available bandwidth and no more. The technology can build an optimized schedule to refresh content with incomplete change data, content with complete change data, or a mixture of content with and without complete change data. It can also re-learn content item change rates from its own schedule execution history and re-compute the refresh schedule, ensuring that this schedule takes into account the latest trends in content item updates.

Abstract: The claimed subject matter provides systems and/or methods that facilitate inferring probability distributions over the destinations and/or routes of a user, from observations about context and partial trajectories of a trip. Destinations of a trip are based on at least one of a prior and a likelihood based at least in part on the received input data. The destination estimator component can use one or more of a personal destinations prior, time of day and day of week, a ground cover prior, driving efficiency associated with candidate locations, and a trip time likelihood to probabilistically predict the destination. In addition, data gathered from a population about the likelihood of visiting previously unvisited locations and the spatial configuration of such locations may be used to enhance the predictions of destinations and routes.

Abstract: This document relates to automated generation of machine learning models, such as neural networks. One example system includes a hardware processing unit and a storage resource. The storage resource can store computer-readable instructions cause the hardware processing unit to perform an iterative model-growing process that involves modifying parent models to obtain child models. The iterative model-growing process can also include selecting candidate layers to include in the child models based at least on weights learned in an initialization process of the candidate layers. The system can also output a final model selected from the child models.

Abstract: The subject disclosure pertains to web searches and more particularly toward influencing resultant content to increase relevancy. The resultant content can be influenced by reconfiguring a query and/or filtering results based on user location and/or context information (e.g., user characteristics/profile, prior interaction/usage temporal, current events, and third party state/context . . . ). Furthermore, the disclosure provides for query execution on at least a subset of designated web content, for example as specified by a user. Still further yet, a localized marketing system is disclosed that provides discount offers to users that match merchant criteria including proximity. A system for actively probing populations of users with different parameters and monitoring responses can be employed to collect data for identifying the best discounts and deadlines to offer to users to achieve desired results.

Abstract: A device can include control channel receiver circuitry to receive airborne vehicle control channel packets, decode circuitry to determine contents of the airborne vehicle control channel packets, transceiver circuitry to provide uplink to and receive downlink data from an airborne vehicle, processing circuitry, and a program for execution by the processing circuitry to perform operations comprising determining, based on data from the receiver circuitry, a received signal strength (RSS) of a signal from each of a plurality of airborne vehicles, determining, for each of the airborne vehicles and based on decoded data from the decode circuitry, a length of time the airborne vehicle will be within transmission range of the transceiver circuitry, determining, for each of the airborne vehicles and based on the determined RSS, determined length of time, and a determined bit-rate, an association metric, and causing association with the airborne vehicle associated with the greatest association metric.

Abstract: A method may include receiving implicitly collected computer interaction data of a user from a computing device; accessing a data store of previously collected computer interaction data, the previously collected computer interaction data correlated with sleep patterns of users; comparing the users implicitly collected computer interaction data to the previously collected computer interaction data; and inferring the user's sleep pattern based on the comparing. The method may provide an indication of real-world cognitive performance that varies throughout the day, and which is influenced by both circadian rhythms, chronotype (morning/evening preference), and prior sleep duration and timing.

Abstract: Velocity information can be beneficial to various entities including other vehicles and a central traffic monitoring and routing system. Vehicles with sensors can serve as velocity probes to update speeds that are shared via a more global service. However, individuals may be reluctant to provide location and velocity information given privacy preferences. Local policies about sharing personal data are described that can be harnessed to enhance privacy while minimizing communication costs. The local data-sharing policies allow devices to monitor their own speeds and locations and to employ models and analyses that determine the value of sharing flow information with a larger service in accordance with privacy preferences, and to make local decisions as to when to respond to broadcasted queries for specific information, while minimizing the redundancy of signals from multiple vehicles.

Abstract: Aspects relate to detecting gestures that relate to a desired action, wherein the detected gestures are common across users and/or devices within a surface computing environment. Inferred intentions and goals based on context, history, affordances, and objects are employed to interpret gestures. Where there is uncertainty in intention of the gestures for a single device or across multiple devices, independent or coordinated communication of uncertainty or engagement of users through signaling and/or information gathering can occur.

Abstract: A device can include control channel receiver circuitry to receive airborne vehicle control channel packets, decode circuitry to determine contents of the airborne vehicle control channel packets, transceiver circuitry to provide uplink to and receive downlink data from an airborne vehicle, processing circuitry, and a program for execution by the processing circuitry to perform operations comprising determining, based on data from the receiver circuitry, a received signal strength (RSS) of a signal from each of a plurality of airborne vehicles, determining, for each of the airborne vehicles and based on decoded data from the decode circuitry, a length of time the airborne vehicle will be within transmission range of the transceiver circuitry, determining, for each of the airborne vehicles and based on the determined RSS, determined length of time, and a determined bit-rate, an association metric, and causing association with the airborne vehicle associated with the greatest association metric.

Abstract: A system with the ability to dynamically compose a sequence of visual views or flows allowing a single object or region, or multiple objects or regions, to be viewed from different perspectives and visual distances is described. The sequence of views can provide smooth flyovers over positions and details on objects that are deemed to be of interest, with changes in zoom level and/or velocity that are functions of the estimated complexity and/or unfamiliarity with features of the object. In an example, a flyover displaying different views on a map of a city arterial system on a small-screened mobile device is composed based on current traffic conditions, swooping up and down with parabolic trajectories, based on distances being traversed, and pausing at times over key traffic jams and other findings of interest based on the estimated visual complexity and predicted atypicality of situations.

Abstract: A system for predicting variability of travel time for a trip at a particular time may utilize a machine learning model including latent variables that are associated with the trip. The machine learning model may be trained from historical trip data that is based on location-based measurements reported from mobile devices. Once trained, the machine learning model may be utilized for predicting variability of travel time. A process may include receiving an origin, a destination, and a start time associated with a trip, obtaining candidate routes that run from the origin to the destination, and predicting, based at least in part on the machine learning model, a probability distribution of travel time for individual ones of the candidate routes. One or more routes may be recommended based on the predicted probability distribution, and a measure of travel time for the recommended route(s) may be provided.

Abstract: A method may include receiving implicitly collected computer interaction data of a user from a computing device; accessing a data store of previously collected computer interaction data, the previously collected computer interaction data correlated with sleep patterns of users; comparing the users implicitly collected computer interaction data to the previously collected computer interaction data; and inferring the user's sleep pattern based on the comparing. The method may provide an indication of real-world cognitive performance that varies throughout the day, and which is influenced by both circadian rhythms, chronotype (morning/evening preference), and prior sleep duration and timing.

Abstract: A stochastic privacy service provider may provide users with a guaranteed upper bound on a probability that personal data will be accessed while enabling the services to collect data that can be used to enhance its services. Users may receive incentives to become participants in a stochastic privacy program. The stochastic privacy provider may employ one or more probabilistic and decision-theoretic methods to determine which participants' personal data should be sought while guaranteeing that the probability of personal data being accessed is smaller than the mutually agreed upon probability of access. The probability of access may be on a per time basis. The stochastic privacy provider may access coalescenses of the personal data of sets of multiple people, where a maximum probability is given for accessing statistical summaries of personal data computed from groups of people that are of at least some guaranteed size.