Abstract: A machine learning feature studio comprises a user interface configured to allow a user to define features associated with an entity. The features are calculated using historical or real-time data stored in an event store and associated with the entity. Visualizations and values of the calculated feature are displayed in the user interface and the user may interact with the features, such as to edit and compare them. The user commits the features to the project associated with a machine learning model and selects to export the project. Feature vectors may are calculated using the committed features and are exported to a production environment.

Abstract: The present invention provides recombinant viral segments comprising an artificial intron, DNA constructs encoding these viral segments, and recombinant viruses comprising these viral segments. Also provided are methods of making and using the recombinant viruses described herein.

Abstract: A system for federated learning comprises a first computing node comprising a first database configured to store data indicative of events associated with a particular subset of a plurality of entities. The first computing node may be configured at least to receive a second set of machine learning features from a second computing node comprising machine learning features generated by data indicative of events associated with a different particular subset of a plurality of entities stored by the second computing node. The first computing node may be configured to generate a first set of machine learning features using the data indicative of events stored in the first database combined with the second set of machine learning features. The first computing node may be configured to cause a machine learning model associated with the first computing node to be trained with the first set of machine learning features.

Abstract: Self-delivering digester 100s with self-delivery of accumulated solids are described. A primary waste vessel includes a feeding port for kitchen waste, and an upper output component that connects to a top of the primary waste vessel. The upper output component includes a gas output path from a top of the upper output component, and a floating solids output path that delivers floating solids that overflow from the top of the primary waste vessel to a secondary vessel thereby preventing clogging of the gas output path.

Abstract: A machine learning feature studio comprises a user interface configured to allow a user to define features associated with an entity. The features are calculated using historical or real-time data stored in an event store and associated with the entity. Visualizations and values of the calculated feature are displayed in the user interface and the user may interact with the features, such as to edit and compare them. The user commits the features to the project associated with a machine learning model and selects to export the project. Feature vectors may are calculated using the committed features and are exported to a production environment.

Abstract: Machine learning feature engineering systems and methods comprise an event ingestion module that receives event data associated with entities. The ingestion module determines which entities are associated with events of the event data. The ingestion module stores the events, grouped by associated entity, in a related event store. A user defines features associated with the entities via an API and/or a feature studio. A feature computation layer determines values for the features based on the grouped events stored to the related event store. The feature computation layer stores the computed feature values and timestamps to a feature store. When new data is received, the feature computation layer computes one or more of the feature values for different times based on the timestamps. Feature vectors are generated using the computed feature values and output to the user via the API and/or feature studio.

Abstract: A system for generating machine learning feature vectors or examples is disclosed herein. The system comprises at least one database configured to store data indicative of events associated with a plurality of entities, an application programming interface (API) server configured to receive a user query from at least one user device, and at least one computing node in communication with the API server and the at least one database. The at least one computing node is configured at least to receive, from the API server and at a first time, a first indication of the user query. The at least one computing node is configured to generate, based at least on the data indicative of events and the first indication of the user query, results associated with the user query, wherein the results comprise one or more feature vectors or examples for use with a machine learning algorithm. The at least one computing node is configured to cause storage of data indicative of the results in the at least one database.

Abstract: A machine learning feature studio comprises a user interface configured to allow a user to define features associated with an entity. The features are calculated using historical or real-time data stored in an event store and associated with the entity. Visualizations and values of the calculated feature are displayed in the user interface and the user may interact with the features, such as to edit and compare them. The user commits the features to the project associated with a machine learning model and selects to export the project. Feature vectors may are calculated using the committed features and are exported to a production environment.

Abstract: A method for generating machine learning training examples using data indicative of events associated with a plurality of entities. The method comprises receiving an indication of one or more selected entities of the plurality of entities, receiving information indicative of selecting one or more prediction times associated with each of the one or more selected entities, and receiving information indicative of selecting one or more label times associated with each of the one or more selected entities. Each of the one or more label times corresponds to at least one of the one or more prediction times, and the one or more label times occur after the corresponding one or more prediction times. Data associated with the one or more prediction times and the one or more label times is extracted from the data indicative of events associated with the plurality of entities.

Abstract: A machine learning feature studio comprises a user interface configured to allow a user to define features associated with an entity. The features are calculated using historical or real-time data stored in an event store and associated with the entity. Visualizations and values of the calculated feature are displayed in the user interface and the user may interact with the features, such as to edit and compare them. The user commits the features to the project associated with a machine learning model and selects to export the project. Feature vectors may are calculated using the committed features and are exported to a production environment.

Abstract: Techniques for managing access control policies are described herein. According to one embodiment, access control policies (ACPs) and access control rules (ACRs) are downloaded from a management server to a network access device (NAD) over the Internet, where the network access device is one of a plurality of network access devices managed by the management server over the Internet. In response to a request from a network client device for entering a network, a device type of the network client device is detected and an ACP identifier is determined based on the device type using the ACRs An ACP is selected from the ACPs based on the ACP identifier and enforced against the network client device. At least the selected ACP is reported to the management server to distribute the selected ACP to other network access devices.

Abstract: A method for generating machine learning training examples using data indicative of events associated with a plurality of entities. The method comprises receiving an indication of one or more selected entities of the plurality of entities, receiving information indicative of selecting one or more prediction times associated with each of the one or more selected entities, and receiving information indicative of selecting one or more label times associated with each of the one or more selected entities. Each of the one or more label times corresponds to at least one of the one or more prediction times, and the one or more label times occur after the corresponding one or more prediction times. Data associated with the one or more prediction times and the one or more label times is extracted from the data indicative of events associated with the plurality of entities.

Abstract: Machine learning feature engineering systems and methods comprise an event ingestion module that receives event data associated with entities. The ingestion module determines which entities are associated with events of the event data. The ingestion module stores the events, grouped by associated entity, in a related event store. A user defines features associated with the entities via an API and/or a feature studio. A feature computation layer determines values for the features based on the grouped events stored to the related event store. The feature computation layer stores the computed feature values and timestamps to a feature store. When new data is received, the feature computation layer computes one or more of the feature values for different times based on the timestamps. Feature vectors are generated using the computed feature values and output to the user via the API and/or feature studio.

Abstract: Techniques for managing access control policies are described herein. According to one embodiment, access control policies (ACPs) and access control rules (ACRs) are downloaded from a management server to a network access device (NAD) over the Internet, where the network access device is one of a plurality of network access devices managed by the management server over the Internet. In response to a request from a network client device for entering a network, a device type of the network client device is detected and an ACP identifier is determined based on the device type using the ACRs An ACP is selected from the ACPs based on the ACP identifier and enforced against the network client device. At least the selected ACP is reported to the management server to distribute the selected ACP to other network access devices.

Abstract: Techniques for managing access control policies are described herein. According to one embodiment, access control policies (ACPs) and access control rules (ACRs) are downloaded from a management server to a network access device (NAD) over the Internet, where the network access device is one of a plurality of network access devices managed by the management server over the Internet. In response to a request from a network client device for entering a network, a device type of the network client device is detected and an ACP identifier is determined based on the device type using the ACRs An ACP is selected from the ACPs based on the ACP identifier and enforced against the network client device. At least the selected ACP is reported to the management server to distribute the selected ACP to other network access devices.

Abstract: Techniques for managing access control policies are described herein. According to one embodiment, access control policies (ACPs) and access control rules (ACRs) are downloaded from a management server to a network access device (NAD) over the Internet, where the network access device is one of a plurality of network access devices managed by the management server over the Internet. In response to a request from a network client device for entering a network, a device type of the network client device is detected and an ACP identifier is determined based on the device type using the ACRs An ACP is selected from the ACPs based on the ACP identifier and enforced against the network client device. At least the selected ACP is reported to the management server to distribute the selected ACP to other network access devices.

Abstract: A system for streaming packet captures over the Internet includes multiple network access devices, each operating as one of a gateway device, a wireless access point, and a network switch, and a management server communicatively coupled to the network access devices over the Internet for managing the network access devices. The management server maintains a persistent hypertext transport protocol (HTTP) connection with each of the network access devices over the Internet. The management server is to generate a bytecode based on a filtering expression for packet captures (PCAPs) representing one or more PCAPs filtering rules, transmit the bytecode to the network access devices without requiring the network access devices to compile the PCAPs filtering rules, receive PCAPs from the network access devices captured by the network access devices based on the PCAPs filtering rules, and merge the PCAPs received from the network access devices into merged PCAPs.

Abstract: A network access device (NAD) receives a UDP packet from a client to be transmitted to a management server over Internet, the UDP packet including a management message. The NAD is one of NADs managed by the management server. The NAD determines whether the management server is reachable using a UDP protocol. The NAD transmits the UDP packet to the management server using the UDP protocol over the Internet if it is determined that the management server is reachable using the UDP protocol. Otherwise, the NAD extracts a UDP payload from the UDP packet, encapsulates the UDP payload within an HTTP POST request, and transmits the HTTP POST request having the UDP payload encapsulated therein to the management server using a HTTP protocol over the Internet.

Abstract: A virtualization system supports secure, controlled execution of application programs within virtual machines. The virtual machine encapsulates a virtual hardware platform and guest operating system executable with respect to the virtual hardware platform to provide a program execution space within the virtual machine. An application program, requiring license control data to enable execution of the application program, is provided within the program execution space for execution within the virtual machine. A data store providing storage of encrypted policy control information and the license control data is provided external to the virtual machine. The data store is accessed through a virtualization system including a policy controller that is selectively responsive to a request received from the virtual machine to retrieve the license control data dependent on an evaluation of the encrypted policy control information.

Abstract: A system for streaming packet captures over the Internet includes multiple network access devices, each operating as one of a gateway device, a wireless access point, and a network switch, and a management server communicatively coupled to the network access devices over the Internet for managing the network access devices. The management server maintains a persistent hypertext transport protocol (HTTP) connection with each of the network access devices over the Internet. The management server is to generate a bytecode based on a filtering expression for packet captures (PCAPs) representing one or more PCAPs filtering rules, transmit the bytecode to the network access devices without requiring the network access devices to compile the PCAPs filtering rules, receive PCAPs from the network access devices captured by the network access devices based on the PCAPs filtering rules, and merge the PCAPs received from the network access devices into merged PCAPs.