Abstract: Systems, methods, and computer-readable media analyzing memory usage in a network node. A network assurance appliance may be configured to determine a hit count for a concrete level rule implemented on a node and identify one or more components of a logical model, wherein each of the one or more components are associated with the concrete level rule. The network assurance appliance may attribute the hit count for the concrete level rule to each of the components of the logical model, determine a number of hardware level entries associated with the each of the one or more components, and generate a report comprising the one or more components of the logical model, the hit count attributed to each of the one or more components of the logical model, and the number of hardware level entries associated with the one or more components of the logical model.

Abstract: Systems, methods, and computer-readable media for fault code aggregation across application-centric dimensions. In an example embodiment, a system obtains respective fault codes corresponding to one or more network devices in a network and maps the one or more network devices and/or the respective fault codes to respective logical policy entities defined in a logical policy model of the network, to yield fault code mappings. The system aggregates the one or more of the fault code mappings along respective logical policy dimensions in the network to yield an aggregation of fault codes across respective logical policy dimensions and, based on the aggregation, presents, for each of the respective logical policy dimensions, one or more hardware-level errors along the respective logical policy dimension.

Abstract: In one embodiment, a device obtains data models and workflow logic for a visual programming environment. The device constructs, based on the data models and workflow logic for the visual programming environment, a metamodel that comprises a knowledge graph. The device makes, using the metamodel, an evaluation of an interaction between a user and the visual programming environment. The device provides, based on the evaluation, visualization data to a user interface of the visual programming environment.

Abstract: In one embodiment, a device identifies a plurality of nodes of a distributed or federated learning system. The device receives model training results from the plurality of nodes. The device determines, based in part on the model training results or information about the plurality of nodes, whether a particular node or subset of nodes in the plurality of nodes provided fraudulent model training results. The device initiates a corrective measure with respect to the particular node or subset of nodes, based on a determination that the particular node or subset of nodes provided fraudulent model training results, in accordance with a policy.

Abstract: In one embodiment, a device identifies, using a semantic reasoning engine, activities in a location, based on sensor data obtained from a plurality of sensors deployed to the location. The device associates the activities with areas of the location in which they occurred. The device makes, using the semantic reasoning engine, an inference about a particular activity, based in part on where that activity occurred. The device raises, based on the inference, an alert regarding the particular activity.

Abstract: In one embodiment, a device presents information regarding an upstream machine learning workload and a downstream machine learning workload via a user interface. The device receives, via the user interface, a request to form a combined machine learning workload by connecting the upstream machine learning workload and the downstream machine learning workload. The device identifies, after receiving the request, a node associated with the upstream machine learning workload and a node associated with the downstream machine learning workload. The device forms the combined machine learning workload by configuring the node associated with the upstream machine learning workload to use one or more connector application programming interfaces to send data from the upstream machine learning workload to the node associated with the downstream machine learning workload for consumption.

Abstract: Systems, methods, and computer-readable media for fault code aggregation across application-centric dimensions. In an example embodiment, a system obtains respective fault codes corresponding to one or more network devices in a network and maps the one or more network devices and/or the respective fault codes to respective logical policy entities defined in a logical policy model of the network, to yield fault code mappings. The system aggregates the one or more of the fault code mappings along respective logical policy dimensions in the network to yield an aggregation of fault codes across respective logical policy dimensions and, based on the aggregation, presents, for each of the respective logical policy dimensions, one or more hardware-level errors along the respective logical policy dimension.

Abstract: In one embodiment, a device receives, from a plurality of training nodes that train a set of machine learning models using local training datasets, bias metrics associated with those machine learning models for each feature of the local training datasets. The device generates aggregated machine learning models over time that aggregate the machine learning models trained by the plurality of training nodes. The device constructs, based on the bias metrics, bias lineages for the aggregated machine learning models. The device provides, based on the bias lineages, a bias lineage for a particular one of the aggregated machine learning models for display.

Abstract: In one embodiment, a device detects a particular activity from sensor data generated by one or more sensors in a sensor network. The device identifies, using a semantic reasoning engine, relevant preceding activities to the particular activity that are relevant to the particular activity. The device makes, using the semantic reasoning engine, an inference about the relevant preceding activities and the particular activity. The device provides an activity timeline for display that indicates the particular activity, the relevant preceding activities, and the inference about the relevant preceding activities and the particular activity.

Abstract: In one embodiment, a device extracts a voice command from audio data captured by a microphone. The device uses a semantic reasoning engine, to determine a goal of the voice command. The device determines that the goal of the voice command is consistent with prior voice commands issued to the device. The device raises an alert when the goal of the voice command is inconsistent with prior voice commands issued to the device.

Abstract: In one embodiment, a device detects an object in an area based on sensor data generated by a plurality of sensors deployed to that area. The device uses a semantic reasoning engine to determine an appearance type of the object, based on the sensor data. The device uses the semantic reasoning engine to determine a behavioral type of the object, based on the sensor data. The device makes, using the semantic reasoning engine, a determination that the behavioral type of the object does not match the appearance type of the object. The device provides an indication of the determination for display.

Abstract: In one embodiment, a device receives, via a user interface, definition data for a machine learning workload. The device identifies groups of training nodes in the network that store training datasets, to perform training roles for the machine learning workload by training machine learning models on their respective training datasets. The device selects a set of intermediate aggregator nodes for the groups of training nodes to aggregate their models. The device provisions the machine learning workload by configuring the groups of training nodes, the set of intermediate aggregator nodes, and a global aggregator node for the set of intermediate aggregator nodes and by configuring channels between training nodes in a group, between the groups of training nodes and the set of intermediate aggregator nodes, and between the set of intermediate aggregator nodes and the global aggregator node.

Abstract: Systems, methods, and computer-readable media for receiving an indication of an equivalence failure, the equivalence failure corresponding to one or more models of network intents. The indication of the equivalence failure is analyzed and one or more constituent intents that caused the equivalence failure are identified, wherein the one or more constituent intents are associated with a model of the one or more models of network intents. The granularity of the equivalence failure and the identified one or more constituent intents is determined, and an event for external consumption is generated, the event based at least in part on the equivalence failure, the granularity of the equivalence failure, and the identified one or more constituent intents.

Abstract: Systems, methods, and computer-readable media for receiving one or more models of network intents, comprising a plurality of contracts between providers and consumers, each contract containing entries with priority values. Each contract is flattened into a listing of rules and a new priority value is calculated. The listing of rules encodes the implementation of the contract between the providers and the consumers. Each entry is iterated over and added to a listing of entries if it is not already present. For each rule, the one or more entries associated with the contract from which the rule was flattened are identified, and for each given entry a flat rule comprising the combination of the rule and the entry is generated, wherein a flattened priority is calculated based at least in part on the priority value of the given one of given entry and the priority value of the rule.

Abstract: Systems, methods, and computer-readable media analyzing memory usage in a network node. A network assurance appliance may be configured to query a node in the network fabric for a number of hardware level entries, stored in memory for the node, that are associated with a concrete level network rule. The network assurance appliance may identify a logical level network intent associated with the concrete level network rule, identify a logical level component of the logical level network intent, and attribute the number of hardware level entries to the logical level component.

Abstract: Systems, methods, and computer-readable media analyzing memory usage in a network node. A network assurance appliance may be configured to obtain reference concrete level rules for a node in the network, obtain implemented concrete level rules for the node from the node in the network, compare the reference concrete level rules with the implemented concrete level rules, and determining that the implemented concrete level rules are not appropriately configured based on the comparison.

Abstract: Systems, methods, and computer-readable media for discovering a network's topology and health. In some examples, a system can obtain, from at least one of a plurality of controllers on a network, a logical model of the network, the logical model including configurations of one or more objects defined for the network. Based on the logical model, the system can identify a respective location of the plurality of controllers in the network and a plurality of nodes in a fabric of the network. Based on the respective location of the plurality of controllers and plurality of nodes, the system can poll the plurality of controllers and plurality of nodes for respective status information, and determine a health and topology of the network based on the logical model, the respective location, and respective status information.

Abstract: Systems, methods, and computer-readable media for localizing faults in a network policy are disclosed. In some examples, a system or method can obtain TCAM rules across a network and use the TCAM rules to perform an equivalency check between the logical model and the hardware model of the network policy. One or more risk models are annotated with output from the equivalency check and the risk models are used to identify a set of policy objects of the network policy that are likely responsible for the faults. The identified set of policy objects are correlated with various logs of the network. Based on the correlation, specific policy objects of the set of policy objects that are associated with physical-level causes of the fault.

Abstract: In one embodiment, a device obtains data models and workflow logic for a visual programming environment. The device constructs, based on the data models and workflow logic for the visual programming environment, a metamodel that comprises a knowledge graph. The device makes, using the metamodel, an evaluation of an interaction between a user and the visual programming environment. The device provides, based on the evaluation, visualization data to a user interface of the visual programming environment.

Abstract: Systems, methods, and computer-readable media analyzing memory usage in a network node. A network assurance appliance may be configured to determine a hit count for a concrete level rule implemented on a node and identify one or more components of a logical model, wherein each of the one or more components are associated with the concrete level rule. The network assurance appliance may attribute the hit count for the concrete level rule to each of the components of the logical model, determine a number of hardware level entries associated with the each of the one or more components, and generate a report comprising the one or more components of the logical model, the hit count attributed to each of the one or more components of the logical model, and the number of hardware level entries associated with the one or more components of the logical model.