Abstract: An apparatus for helping with multicast domain name service (MDNS) discovery includes one or more processors configured to receive a first MDNS query from the resource-seeking device, receive a first MDNS response from the resource-providing device, and generate a second MDNS response according to the first MDNS response. The second MDNS response is generated at least by including a resource record from the first MDNS response and setting a time-to-live (TTL) value of the resource record in the second MDNS response to be lower than an original TTL value as specified for the resource record in the first MDNS response. The second MDNS response is sent to the resource-seeking device in response to the first MDNS query. A hospitality establishment may thereby soft assign a media device to a user device while retaining the ability to change the media device assigned to the user device.

Abstract: Various techniques for facilitating communication with and across a clinical environment and a cloud environment are described. For example, a method for tagging messages with facility identifiers in a manner that does not require changing the identifiers when logically re-arranging the facilities. A connectivity adapter in the clinical environment can receive a message from an infusion pump and tag the message with only permanent IDs such that when the facility in which the connectivity resides is categorized under a different system or region, the identifiers in the message need not be updated.

Abstract: Disclosed herein is an artificial intelligence server for updating an artificial intelligence model by merging a plurality of pieces of update information including a memory configured to store a first artificial intelligence model, a communication modem configured to communicate with a plurality of artificial intelligence apparatuses, and a processor configured to transmit the first artificial intelligence model to the plurality of artificial intelligence apparatuses, receive, from at least one of the plurality of artificial intelligence apparatuses, first update information of the first artificial intelligence model or second update information of a second artificial intelligence model updated from the first artificial intelligence model, select third update information to be used to update the first artificial intelligence model from the first update information and the second update information, and update the first artificial intelligence model using the third update information.

Abstract: An architecture for dynamically selecting and routing traffic from Internet of things (IoT) devices and sensors to the nearest or most proximate IoT hub device. A method can comprise receiving a connection request from a user device; retrieving address data representing a network device of a group of network devices; and sending the address data to the user device.

Abstract: Embodiments of a method are disclosed. The method includes performing a batch of decentralized deep learning training for a machine learning model in coordination with multiple local homogenous learners on a deep learning training compute node, and in coordination with multiple super learners on corresponding deep learning training compute nodes. The method also includes exchanging communications with the super learners in accordance with an asynchronous decentralized parallel stochastic gradient descent (ADPSGD) protocol. The communications are associated with the batch of deep learning training.

Abstract: Techniques for quantizing training data sets using machine learning (ML) model metadata are provided. In one set of embodiments, a computer system can receive a training data set comprising a plurality of features and a plurality of data instances, where each data instance includes a feature value for each of the plurality of features. The computer system can further train a machine learning (ML) model using the training data set, where the training results in a trained version of the ML model, and can extract metadata from the trained version of the ML model pertaining to the plurality of features. The computer system can then quantize the plurality of data instances based on the extracted metadata, the quantizing resulting in a quantized version of the training data set.

Abstract: A system and method for sending an image to a user device based on the context of a user of the device are provided. An image to be sent to a user device may be obtained. The context of the user may be determined. The image may be analyzed to detect and prioritize objects in the image based on the context of the user. The image may be encoded such that objects are rendered on the user device in an order based on the prioritization. The encoded image may be sent to the user device.

Abstract: A lateral movement identification tool analyzes communications sent and received from a local host to identify potential instances of lateral movement. When the host-based lateral movement identification tool identifies a host to host connection, the tool processes one or more artificial intelligence algorithms to analyze information from local network resources including a directory service, a local network system such as a network basic input/output system, a domain name system, and event logs. The lateral movement identification tool correlates the aggregated information with identified host to host messaging and sends alerts when lateral movement is suspected. Alerts may be either presented locally or provided to a central console based on configuration information.

Abstract: A computing network has a sensor, a first processor in a first computing network location, and a second processor in a second computing network location, the second computing network location further from the sensor than the first computing network location. The first processor is configured to receive sensor data from the sensor and configured to operate a first machine learning model to make a first inference based on the sensor data. The second processor is configured to receive the sensor data and to operate a second machine learning model to make a second inference based on the sensor data in response to a trigger. The computing network is configured to collate and process the first and second inferences to make an aggregated inference.

Abstract: An indication is used to control how message service information is routed over different domains. For example, an access terminal may be configured with an indication that indicates that a message service is preferred to be invoked over an IP domain or that the message service is not be invoked over the IP domain. The access terminal then delivers message service information based on the value of the indication. In some cases, a network entity generates the indication and sends the indication to the access terminal. In some cases, a domain for delivery of message service information is selected based on a domain that was selected for particular type of traffic.

Abstract: Techniques regarding one or more automated machine learning processes that analyze time series data are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a time series analysis component that selects a machine learning pipeline for meta transfer learning on time series data by sequentially allocating subsets of training data from the time series data amongst a plurality of machine learning pipeline candidates.

Abstract: Provided is a system and method for tuning an array of sensors to enable selection of the most suitable sensors for a target application. After extracting features from sensor raw data, the extracted features are ranked with gradient boosting decision trees to assign an importance value to each extracted feature. A threshold value for the entire set of extracted features is calculated and an importance score is calculated for the individual sensors of the array. Individual sensors with an importance score on or above the threshold value are selected for the target application.

Abstract: A training system may create and train a machine learning model with knowledge transfer. The knowledge transfer may transfer knowledge that is acquired by another machine learning model that has been previously trained to the machine learning model that is under training. The knowledge transfer may include a combination of representation transfer and instance transfer, the two of which may be performed alternatingly. The instance transfer may further include a filter mechanism to selectively identify instances with a satisfactory performance to implement the knowledge transfer.

Abstract: Systems for intelligent sorting of time series data for improved contextual messaging are included herein. An intelligent sorting server may receive time series data comprising a plurality of chat messages. The intelligent sorting server may determine a first order of the plurality of chat messages based on a chronologic order. The intelligent sorting server may use one or more machine learning classifiers to identify candidates for reordering the chat messages. The intelligent sorting server may generate a second order of the chat messages based on the identified candidates for reordering. Accordingly, the intelligent sorting server may present, to a client device, a transcript of the chat messages associated with the second order and an indication that at least one chat message has been repositioned.

Abstract: A method including extracting, from an input, supported data. The input includes outputs from machine learning models in different formats. The supported data includes a subset of the input after data normalization. The method also includes inferring, from the supported data, data types to be used with respect to generating metrics for the machine learning models. The method also includes generating, from the supported data and using the data types, a relational event including the supported data. The relational event further includes a first data structure object including the types and having a first data structure different than the different formats. The method also includes calculating, using the supported data in the first data structure, the metrics for the machine learning models. The method also includes generating, from the relational event, a monitoring event. The monitoring event includes a second data structure object segmented into data buckets storing the metrics.

Abstract: Systems and methods for effectively managing exit nodes are provided. The exemplary systems and methods use a Supernode to examine an Exit Node through sending and receiving a request to a Target. Information about the exit node is then stored into the Supernode. According to the information provided from the Supernode, the Exit Nodes Database systemizes the proxies according to availability and provides available exit nodes to a User Device.

Abstract: Techniques for iterative model training and deployment for automated learning systems are described. A method of iterative model training and deployment for automated learning systems comprises generating training data based on inference data, provided by a first version of a model hosted at an endpoint of a machine learning service, and feedback data, received from a client application, using an identifier associated with the inference data and the feedback data, generating a second version of the model using the training data, and deploying the model to the endpoint of the machine learning service.

Abstract: Aspects of the present disclosure involve systems and methods for a service activation system in a telecommunications network that utilizes one or more generic container files for building the configuration file to instantiate the service on the network. A request for service from a network may be received from an order entry system that includes specific information about the requested service. A collection of generic configuration files may be selected based on the information included in the service order and arranged to build a configuration file to be executed on the network. The service activation system may also include a component or group of components to verify a received service order and alter the service order with default information or data where applicable. The configuration file may also be executed on the network through one or more drivers communicating with the affected devices to configure the one or more network devices.

Abstract: Techniques for adaptive asynchronous federated learning are described herein. An aspect includes providing a first version of a global parameter to a first client and a second client. Another aspect includes receiving, from the first client, a first gradient, wherein the first gradient was computed by the first client based on the first version of the global parameter and a respective first local dataset of the first client. Another aspect includes determining whether the first version of the global parameter matches a most recent version of the global parameter. Another aspect includes, based on determining that the first version of the global parameter does not match the most recent version of the global parameter, selecting a version of the global parameter. Another aspect includes aggregating the first gradient with the selected version of the global parameter to determine an updated version of the global parameter.

Abstract: A system includes a memory; and a processor configured to train a first machine learning model based on the first dataset labeling; provide the second dataset to the trained first machine learning model to generate an updated second dataset including an updated second dataset labeling, determine a first difference between the updated second dataset labeling and the second dataset labeling; train a second machine learning model based on the updated second dataset labeling if the first difference is greater than a first threshold value; provide the first dataset to the trained second machine learning model to generate an updated first dataset including an updated first dataset labeling, determine a second difference between the updated first dataset labeling and the first dataset labeling; and train the first machine learning model based on the updated first dataset labeling if the second difference is greater than a second threshold value.