Abstract: Systems and methods for sports data crowdsourcing and analytics is provided. In one embodiment, a method for at least one server for generating verified sports data of a sporting event is provided, the method comprising: receiving, at the server(s), first audio data captured by a microphone of a first client device; receiving, at the server(s), second audio data captured by a microphone of a second client device; synching the first audio data by arranging the first audio data based on at least one parameter; synching the second audio data by arranging the second audio data based on the at least one parameter; and generating the verified sports data by comparing, based on the at least one parameter, the first audio data and the second audio data to determine that a stat within the sporting event is verified.

Abstract: This disclosure describes techniques that include using an automatically trained machine learning system to generate a prediction. In one example, this disclosure describes a method comprising: based on a request for the prediction: training each respective machine learning (ML) model in a plurality of ML models to generate a respective training-phase prediction in a plurality of training-phase predictions; automatically determining a selected ML model in the plurality of ML models based on evaluation metrics for the plurality of ML; and applying the selected ML model to generate the prediction based on data collected from a network that includes a plurality of network devices.

Abstract: A computer-implemented method includes establishing, by a computer device, an activity to be performed by a robot; determining, by the computer device, a required knowledge that is required for the robot to perform the activity; comparing, by the computer device, the required knowledge to a current knowledge of the robot to establish an additional learning that is needed for the robot to perform the activity; requesting, by the computer device, the additional learning; directing, by the computer device, retrieval of the additional learning to the robot if the additional learning is available for retrieval; and requesting, by the computer device, that the additional learning be created if the additional learning is not available for retrieval.

Abstract: A download module accesses a download queue including at least two file download requests from an application running on a client device of a server. The application and each of the file download requests is associated with a context that comprises a set of context components that each indicates a part of the application. The file download request context components indicate parts of the application that use the requested file and the application context components indicate parts of the application that are active. The download module ranks each of the file download requests based on a comparison of the respective file download request context components of each file download request to the application context components of the application. The download module then selects two or more file download requests in the download queue for concurrent execution based on the respective rankings of the file download requests in the download queue.

Abstract: System and method for adaptive training of a machine learning system processing textual data. For example, a method for adaptive training of a machine learning system configured to predict answers to questions associated with textual data includes receiving predicted answers to questions associated with textual data. The predicted answers are generated based at least in part on one or more first models of a machine learning system. The one or more first models are associated with a first accuracy score. The method further includes determining based at least in part on a quality control parameter whether an evaluation of the questions by one or more external entities is required. In response to determining based at least in part on the quality control parameter that an evaluation of the questions by one or more external entities is required, the questions associated with the textual data and the textual data are sent to the one or more external entities for evaluation.

Abstract: Apparatuses, methods, systems, and program products are disclosed for optimizing aggregation routing over a network. An apparatus includes a processor and a memory that stores code executable by the processor. The code is executable by the processor to select a data aggregator server from a plurality of data aggregator servers to service a request for aggregated account data based on a plurality of factors associated with each of the plurality of data aggregator servers, format a request for the aggregated account data to be compatible with the selected data aggregator server, route the formatted request over the network to the selected data aggregator server, receive the requested aggregated account data over the network from the selected data aggregator server, populate a form for a personal financial manager (“PFM”) with the aggregated account data, output the populated form to the PFM, and present the aggregated account data to a user.

Abstract: A first communicating entity determines session state parameters of a security protocol session between itself and a second communicating entity. The first entity uses the session state parameters to transmit a first set of messages of the session to the second entity via a first communication mechanism. The first entity also uses the session state parameters to transmit a second set of messages of the session to the second entity via a second communication mechanism.

Abstract: A system and method for providing high availability for a thin-provisioned container cluster includes a memory, one or more processors in communication with the memory, a scheduler executing on the one or more processors, and a spot instance market monitor. The spot instance market monitor receives market information about spot instances in a cloud system at a first time. The spot instances are available to a client at the first time. The spot instance market monitor determines, based on the market information, a respective reliability value for each of the spot instances at the first time. Then, the scheduler selects one spot instance among the spot instances based on the reliability value of the spot instance. In response to the selection of the spot instance, the scheduler schedules a container on the spot instance and executes the container on the spot instance.

Abstract: Techniques are described for enabling users of a service provider network to create and configure “application profiles” that include parameters related to execution of user workloads at provider substrate extensions. Once an application profile is created, users can request the deployment of user workloads to provider substrate extensions by requesting instance launches based on a defined application profile. The service provider network can then automate the launch and placement of the user's workload at one or more provider substrate extensions using edge-optimized compute instances (e.g., compute instances tailored for execution within provider substrate extension environments).

Abstract: Systems, computer-implemented methods, and computer program products to facilitate data protection distributed learning are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a local parameter component that employs an agent to compute local model parameters based on data of the agent. The computer executable components can further comprise a global parameter component that employs the agent to estimate a global model parameter based on the local model parameters and model parameters of one or more neighbor agents.

Abstract: Techniques for synthetic data generation in computer-based reasoning systems are discussed and include receiving a request for generation of synthetic data based on a set of training data cases. One or more focal training data cases are determined. For undetermined features (either all of them or those that are not subject to conditions), a value for the feature is determined based on the focal cases. In some embodiments, the generation of synthetic data may be conditioned on values of features, preserved features, such as unique identifiers, previous-in-time features, and using the other techniques discussed herein.

Abstract: According to examples, an apparatus may include a processor that may generate a migration assessment for resources of a computer system. In particular, the apparatus may logically divide topological information to facilitate identification of a resource, components used by the resource, and dependencies. The system further enables users to specify user-defined migration parameters that specify the migration. For instance, the parameters may specify a cost associated with the migration of the component, a license model of the component, a security requirement of the component, a performance of the component, a customization of the component, or requirement of the component. Migration assessments and decisions may be stored to train machine-learned models. For instance, the model may assess whether a parameter will be satisfied by using a certain cloud service and whether substitutes have sufficiently satisfied dependencies based on observed migration assessments and actual migrations.

Abstract: A resource configuration method and apparatus for heterogeneous cloud services are provided. The method may include: establishing a basic model with a general structure for at least two heterogeneous cloud services, where the basic model comprises a trend model and a periodic model; determining a cloud service in the at least two cloud services as a target cloud service, and acquiring a target historical data set of the target cloud service; training the trend model and the periodic model using the target historical data set; generating a target prediction model corresponding to the target cloud service based on the trained trend model and the trained periodic model; and generating, based on the target prediction model, a resource amount demanded by the target cloud service in a future time period, and configuring resources for the target cloud service according to the demanded resource amount.

Abstract: A non-transitory computer-readable recording medium stores therein a predicting program that causes a computer to execute: receiving input data to be subjected to prediction; and generating, from training data sets each having explanatory variables and an objective variable, a prediction result, by using a hypothesis set and respective weights of hypotheses included in the hypothesis set, the hypotheses each being formed of a combination of the explanatory variables, classifying any of the training data sets and satisfying a specific condition, the weights being learnt based on whether each of the hypotheses holds true for each of the training data sets. The generating includes determining a value of a variable included in a pseudo-Boolean function such that a probability satisfies a predetermined standard, the probability being a probability that the prediction result satisfies the specific condition, the pseudo-Boolean function including variables corresponding to the explanatory variables.

Abstract: Systems and techniques are disclosed for a centralized platform for enhanced automated machine learning using disparate datasets. An example method includes receiving user specification of one or more data sources to be integrated with the system, the data sources storing datasets to be utilized to train one or more machine learning models by the system, and the datasets reflecting user interaction data. A dataset is imported from the data source, and machine learning models are automatically trained based a particular machine learning model recipe of a plurality of machine learning model recipes. A first trained machine learning model is implemented, with the system being configured to respond to queries based on the implemented machine learning model, and with the responses including personalized recommendations.

Abstract: A method includes assigning unique symbols respectively to potential interactions with a website. The method includes obtaining asserted interaction symbol sequences of multiple browsing sessions, respectively. Each browsing session corresponds to a visitor of the website. For each browsing session, the asserted interaction symbol sequence of the respective browsing session is a sequence of symbols, from among the unique symbols, that corresponds, respectively, to a sequence of asserted interactions with the web site visited during the respective browsing session by the corresponding visitor. The method includes generating a master string including the asserted interaction symbol sequences by concatenating the asserted interaction symbol sequences with sentinel symbols together such that at least one sentinel symbol exists between each consecutive pair of asserted interaction symbol sequences. The method includes generating a suffix array corresponding to the master string.

Abstract: A model designer improves the security of a machine learning model in certain embodiments. Instead of storing the model in a central location, the training data used to build and train the model is stored across several different databases and/or datacenters. The training data is divided into portions and stored as a circular linked list across these databases and/or datacenters. The model designer retrieves the training data and incrementally builds and trains the model using the training data. The incremental error and bias of the model is used to locate training data between datacenters. Additionally, fake training data is appended to the circular linked list and the model designer tracks how much training data is used before hitting fake training data.

Abstract: An information processing apparatus configured to receive message information from a terminal device, and transmit responding message information to the terminal device based on setting information in which query information and answer information are associated with each other, switch a state between a first state and a second state, the first state being a state in which the message information is to be received from the terminal device and a change of the setting information is to be received, the second state being a state in which the message information is not to be received and a change of the setting information is to be received, and when switching from the second state to the first state is performed, transmit the responding message information based on the setting information for which the change has been received in the second state before the switching is performed.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that, upon request for a trait-intersection count of users (or other digital entities) corresponding to traits for a target time period, use a machine-learning model to analyze a semantic-trait embedding of the traits and to generate an estimated trait-intersection count of such entities sharing the traits for the target time period. By applying a machine-learning model trained to estimate trait-intersection counts, the disclosed methods, non-transitory computer readable media, and systems can analyze both a semantic-trait embedding of traits and an initial trait-intersection count of trait-sharing entities for an initial time period to estimate the trait-intersection count for the target time period.

Abstract: A network interface device has an input configured to receive data from a network. The data is for one of a plurality of different applications. The network interface device also has at least one processor configured to determine which of a plurality of available different caches in a host system the data is to be injected by accessing to a receive queue comprising at least one descriptor indicating a cache location in one of said plurality of caches to which data is to be injected, wherein said at least one descriptor, which indicates the cache location, has an effect on subsequent descriptors of said receive queue until a next descriptor indicates another cache location. The at least one processor is also configured to cause the data to be injected to the cache location in the host system.