Abstract: In one implementation, a device receives a request to generate a set of video clips that depict a specified classification label. The device represents each of one or more objects depicted in a particular video clip over time as a set of timeseries of key points associated with that object. The device makes a determination as to whether the particular video clip depicts the specified classification label by analyzing the set of timeseries of key points associated with the particular video clip and in accordance with one or more constraint parameters. The device labels, based on the determination, the particular video clip with the specified classification label for inclusion in the set of video clips that depict the specified classification label.

Abstract: In one implementation, a device obtains a base machine learning model trained to label input data using a plurality of classes. The device receives a deployment task from a user interface indicative of a subset of one or more of the plurality of classes to be identified by a new model for deployment. The device selects a quantization level based on a difficulty associated with the deployment task. The device generates the new model for deployment that is quantized from the base machine learning model and specialized to label its input data using only the subset of one or more of the plurality of classes.

Abstract: In one embodiment, a device represents each of a plurality of objects depicted in video data captured by a plurality of cameras over time as a set of key points associated with that object. The device forms, for each of the plurality of objects, a set of timeseries of the set of key points associated with that object. The device performs reidentification of a particular one of the plurality of objects across video data captured by two or more of the plurality of cameras by matching sets of timeseries of key points associated with that object derived from video data captured by two or more of the plurality of cameras. The device provides an indication of the reidentification for display to a user.

Abstract: In one embodiment, a device maintains a metamodel that describes a monitored system. The metamodel comprises a plurality of layers ranging from a sub-symbolic space to a symbolic space. The device tracks updates to the metamodel over time. The device updates the metamodel based in part on sub-symbolic time series data generated by the monitored system. The device receives, from a learning agent, a request for the updates to a particular layer of the metamodel associated with a specified time period. The device provides, to the learning agent, data indicative of one or more updates to the particular layer of the metamodel associated with the specified time period.

Abstract: In one embodiment, a device represents each of a plurality of objects depicted in video data over time as a set of timeseries of key points associated with that object. The device forms groups of objects based on their associated sets of timeseries. The device identifies an anomalous behavior of a particular group from among the groups of objects, based on their constituent timeseries of coordinate points. The device provides an alert regarding the anomalous behavior to a user interface for review.

Abstract: In one embodiment, a device represents spatial characteristics over time of an object in video data as one or more timeseries. The device detects an event based on a rate of change of behavioral regimes associated with different portions of the one or more timeseries. The device selects contextual data for the event that comprises spatial timeseries information for different types of objects or different activities. The device provides an alert for the event to a user interface regarding the event that includes the contextual data.

Abstract: In one embodiment, a device tracks an object in video data captured by one or more cameras. The device represents spatial characteristics of the object over time as one or more timeseries. The device associates different portions of the one or more timeseries with behavioral regimes of the object. The device provides a portion of the video data for display as part of an alert that is based on a rate of change of transitions between the behavioral regimes of the object.

Abstract: In one embodiment, a student agent identifies a topic of interest. The student agent issues a set of one or more questions to a teacher agent regarding the topic of interest. The student agent receives, from the teacher agent, answer data in response to the set of one or more questions. The student agent uses the answer data to generate a neuro-symbolic metamodel that comprises a semantic reasoner and a sub-symbolic layer.

Abstract: In one embodiment, a device receives, from a requestor, a request for a set of ground truth examples of a particular type to be used to train a machine learning model. The request includes context data regarding a location to be analyzed by the machine learning model. The device identifies, based on the request, the set of ground truth examples using a metamodel comprising a semantic reasoner and a sub-symbolic layer. The device associates labels with the set of ground truth examples. The device provides, to the requestor, the set of ground truth examples and their labels.

Abstract: In one embodiment, a device maintains a metamodel that describes a monitored system. The metamodel comprises a plurality of layers ranging from a sub-symbolic space to a symbolic space. The device tracks updates to the metamodel over time. The device updates the metamodel based in part on sub-symbolic time series data generated by the monitored system. The device receives, from a learning agent, a request for the updates to a particular layer of the metamodel associated with a specified time period. The device provides, to the learning agent, data indicative of one or more updates to the particular layer of the metamodel associated with the specified time period.

Abstract: In one embodiment, a device tracks objects in video data captured by one or more cameras in a location. The device represents spatial characteristics of the objects over time as timeseries. The device associates different portions of the timeseries with behavioral regimes of the objects. The device makes a determination that one of the objects is a reflection of another of the objects, based on a correlation between changes of their respective behavioral regimes.

Abstract: In one embodiment, a device represents spatial characteristics of an object depicted in video data over time as one or more timeseries. The device associates different portions of the one or more timeseries with behavioral regimes of the object. The device generates ground truth labels for frames of the video data based on changes in the behavioral regimes of the object associated with those frames. The device trains a self-supervised model to detect an event depicted in the video data using the ground truth labels and their associated frames.

Abstract: In one embodiment, a device represents spatial characteristics over time of an object in video data as one or more timeseries. The device detects an event based on a rate of change of behavioral regimes associated with different portions of the one or more timeseries. The device selects contextual data for the event that comprises spatial timeseries information for different types of objects or different activities. The device provides an alert for the event to a user interface regarding the event that includes the contextual data.

Abstract: In one embodiment, a device tracks an object in video data captured by one or more cameras. The device represents spatial characteristics of the object over time as one or more timeseries. The device associates different portions of the one or more timeseries with behavioral regimes of the object. The device provides a portion of the video data for display as part of an alert that is based on a rate of change of transitions between the behavioral regimes of the object.

Abstract: In one embodiment, a first deep fusion reasoning engine (DFRE) agent in a network receives first sensor data from a first set of one or more sensors in the network. The first DFRE agent translates the first sensor data into symbolic data. The first DFRE agent applies, using a symbolic knowledge base maintained by the first DFRE agent, symbolic reasoning to the symbolic data to make an inference regarding the first sensor data. The first DFRE agent updates, based on the inference regarding the first sensor data, the knowledge base. The first DFRE agent propagates the inference to one or more other DFRE agents in the network.

Abstract: In one embodiment, a video analysis service receives video data captured by one or more cameras at a particular location. The service applies a neural network-based model to portions of the video data, to identify objects within the video data. The service maps outputs of the neural network-based model to symbols using a conceptual space. The outputs of the model comprise the identified objects. The service applies a symbolic reasoning engine to the symbols, to generate an alert. The service sends the alert to a user interface in conjunction with the video data.

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 deep fusion reasoning engine receives network telemetry data collected from a network. The deep fusion reasoning engine learns resource utilizations for different heuristic packages that can be used in the network to evaluate operation of the network. The deep fusion reasoning engine selects one of the heuristic packages based on the resource utilizations learned for the different heuristic packages. The selected heuristic package comprises a subservice and a set of rules to be evaluated. The deep fusion reasoning engine deploys the selected heuristic package for execution by a device in the network to evaluate operation of the network using the set of rules.

Abstract: In one embodiment, a device obtains data regarding generation of an artificial intelligence model. The device analyzes the data using a neuro-symbolic metamodel, to match the data to one or more concepts of a knowledge graph of the neuro-symbolic metamodel. The device makes one or more inferences about the artificial intelligence model, by applying a semantic reasoning engine to the one or more concepts of the knowledge graph. The device causes, based on the one or more inferences, generation of a replacement artificial intelligence model for the artificial intelligence model.

Abstract: In one embodiment, a device converts video data into a set of tracklets, each tracklet representing a different object depicted in the video data. The device identifies a particular object depicted in the video data as being an attractor or repulsor with respect to one or more other objects depicted in the video data, based on an analysis of their respective tracklets. The device makes, using a semantic reasoning engine, an inference about the video data, based in part on the particular object being identified as an attractor or repulsor. The device provides data based on the inference for display.