An Artificial Intelligence (AI)-based data matching and alignment system identifies similar data sources for a target data source from a data corpus and generates a knowledge graph that enables downstream applications seamless access to data in the data corpus. The system extracts column features at different levels for the target data source and a plurality of data sources from the data corpus. Feature matrices are built from the features of the target data source and the plurality of data sources. Candidate data sources similar to the target data source are filtered from the plurality of data sources using the feature matrices. The tree-based similarity is estimated and K Nearest Neighbor (KNN) graphs are built to identify columns from the candidate data sources that are similar to columns of the target data source to build the knowledge graph.

In one embodiment, a method of machine learning and/or image processing for spectral object classification is described. In another embodiment, a device is described for using spectral object classification. Other embodiments are likewise described.

A system and method are provided that use context awareness with device-dependent training to improve precision while reducing classification latency and the need for additional computing, such as by relying on cloud-based processing. Moreover, the following can leverage signal analysis with multiple sensors and secondary validation in a multi-modal approach to track passive events that would otherwise be difficult to identify using classical methods. In at least one implementation, the system and method described herein can leverage low power sensors and integrate already available human behavior in modular algorithms isolating specific context to reduce user interact time and training to a minimum.

A convolutional neural network system includes a sensor and a controller, wherein the controller is configured to receive an image from the sensor, divide the image into patches, each patch of size p, extract, via a first convolutional layer, a feature map having a number of channels based on a feature detector of size p, wherein the feature detector has a stride equal to size p, refine the feature map by alternatingly applying depth-wise convolutional layers and point-wise convolutional layers to obtain a refined feature map, wherein the number of channels in the feature map and the size of the feature map remains constant throughout all operations in the refinement; and output the refined feature map.

In various examples, a set of object trajectories may be determined based at least in part on sensor data representative of a field of view of a sensor. The set of object trajectories may be applied to a long short-term memory (LSTM) network to train the LSTM network. An expected object trajectory for an object in the field of view of the sensor may be computed by the LSTM network based at least in part an observed object trajectory. By comparing the observed object trajectory to the expected object trajectory, a determination may be made that the observed object trajectory is indicative of an anomaly.

A method by one or more network devices executing one or more smart contracts stored in a blockchain for anonymizing faces appearing in digital media content. The method includes obtaining, for each of a plurality of users, a facial model associated with that user, obtaining digital media content digital media content, determining whether that detected face matches the face of any of the plurality of users based on applying one or more of the facial models associated with the plurality of users to that detected face, anonymizing that detected face to generate an anonymized face in response to a determination that that detected face matches the face of one of the plurality of users, and providing the anonymized face to the media platform.

Systems, methods and apparatus for sematic segmentation of 3D point clouds using deep neural networks. The deep neural network generally has two primary subsystems: a multi-branch cascaded subnetwork that includes an encoder and a decoder, and is configured to receive a sparse 3D point cloud, and capture and fuse spatial feature information in the sparse 3D point cloud at multiple scales and multi hierarchical levels; and a spatial feature transformer subnetwork that is configured to transform the cascaded features generated by the multi-branch cascaded subnetwork and fuse these scaled features using a shared decoder attention framework to assist in the prediction of sematic classes for the sparse 3D point cloud.

A mechanism is described for facilitating recognition, reidentification, and security in machine learning at autonomous machines. A method of embodiments, as described herein, includes facilitating a camera to detect one or more objects within a physical vicinity, the one or more objects including a person, and the physical vicinity including a house, where detecting includes capturing one or more images of one or more portions of a body of the person. The method may further include extracting body features based on the one or more portions of the body, comparing the extracted body features with feature vectors stored at a database, and building a classification model based on the extracted body features over a period of time to facilitate recognition or reidentification of the person independent of facial recognition of the person.

A system/process/computer program product for building multi-representational learning models for static analysis of source code includes receiving training data, wherein the training data includes a set of source code files for training a multi-representational learning (MRL) model for classifying malicious source code and benign source code based on a static analysis; generating a first feature vector based on a set of characters extracted from the set of source code files; generating a second feature vector based on a set of tokens extracted from the set of source code files; and performing an ensemble of the first feature vector and the second feature vector to form a target feature vector for classifying malicious source code and benign source code based on the static analysis.

Systems and methods are disclosed for identifying target graphs that have nodes or neighborhoods of nodes (sub-graphs) that correspond with an input query graph. A visual analytics system supports human-in-the-loop, example-based subgraph pattern search utilizing a database of target graphs. Users can interactively select a pattern of nodes of interest. Graph neural networks encode topological and node attributes in a graph as fixed length latent vector representations such that subgraph matching can be performed in the latent space. Once matching target graphs are identified as corresponding to the query graph, one-to-one node correspondence between the query graph and the matching target graphs.