Abstract: A counterfeit detection system provides an artificial intelligence (AI) platform that implements a Generative Adversarial Network (GAN) to classify an image as one of a fake or genuine item and integrates a Classification Activation Module (CAM) to refine counterfeit detection. The GAN may include a generator that generates simulated counterfeit images for a discriminator. The discriminator may be trained to identify faked items by learning from the simulated counterfeit images and/or images of actual faked items. The discriminator may implement a deep neural network of convolutional layers that each analyze a region of an image and produce a weighted output that contributes to the classification based on the analyzed region. The CAM may identify the regions and weights relied upon by the discriminator, provide corresponding heatmaps to subject matter experts, receive annotations from the subject matter experts, and use the annotations as feedback to refine the classifier of the discriminator.

Abstract: An identification and management system for log entries may filter historical data and generate closed log entries as a reference dataset. A dynamic learning engine may perform statistical modelling using the reference dataset to assign predetermined categories to each of a number of open log entries. An automation index may be generated for each of the open log entries. The automation index is indicative of accuracy of the assigned categories. Some of the open log entries may be identified as priority log entries which are representative of a group of the open log entries. The assigned category of the priority log entries may be analyzed for accuracy and the results of the analysis may be used to train the statistical model so that the open log entries may be iteratively assigned and re-assigned a category until the category of each open log entry reaches a desired accuracy.

Abstract: A device receives images of a video stream, models for objects in the images, and physical property data for the objects, and maps the models and the physical property data to the objects in the images to generate augmented data sequences. The device applies different physical properties to the objects in the augmented data sequences to generate augmented data sequences with different applied physical properties, and trains a machine learning (ML) model based on the images to generate a first trained ML model. The device trains the ML model, based on the augmented data sequences with the different applied physical properties, to generate a second trained ML model, and compares the first trained ML model and the second trained ML model. The device determines whether the second trained ML model is optimized based on the comparison, and provides the second trained ML model when optimized.

Abstract: A device receives images of a video stream, models for objects in the images, and physical property data for the objects, and maps the models and the physical property data to the objects in the images to generate augmented data sequences. The device applies different physical properties to the objects in the augmented data sequences to generate augmented data sequences with different applied physical properties, and trains a machine learning (ML) model based on the images to generate a first trained ML model. The device trains the ML model, based on the augmented data sequences with the different applied physical properties, to generate a second trained ML model, and compares the first trained ML model and the second trained ML model. The device determines whether the second trained ML model is optimized based on the comparison, and provides the second trained ML model when optimized.

Abstract: Implementations are directed to providing categorization of transactional data, and include actions of providing a plurality of word embeddings based on domain-relevant text data, clustering word embeddings of the plurality of word embeddings into a plurality of clusters, receiving, in real-time, transactional data representative of a transaction, providing a category that is to be assigned to the transaction based on the transactional data, and the plurality of clusters, processing the category, the transactional data, the text data, and the plurality of clusters using a semantic search to provide reason text data, the reason text data representing a reason for selection of the category assigned to the transaction, and storing the transaction data, the category, and the reason text data in a transaction database.

Abstract: A counterfeit detection system provides an artificial intelligence (AI) platform that implements a Generative Adversarial Network (GAN) to classify an image as one of a fake or genuine item and integrates a Classification Activation Module (CAM) to refine counterfeit detection. The GAN may include a generator that generates simulated counterfeit images for a discriminator. The discriminator may be trained to identify faked items by learning from the simulated counterfeit images and/or images of actual faked items. The discriminator may implement a deep neural network of convolutional layers that each analyze a region of an image and produce a weighted output that contributes to the classification based on the analyzed region. The CAM may identify the regions and weights relied upon by the discriminator, provide corresponding heatmaps to subject matter experts, receive annotations from the subject matter experts, and use the annotations as feedback to refine the classifier of the discriminator.

Abstract: A device may receive multimedia data, metadata, and/or policy data. The device may process the policy data using a first set of techniques to determine a first set of embeddings for the policy data. The device may process the multimedia data or the metadata using a second set of techniques to determine a second set of embeddings for the multimedia data or the metadata. The device may process the first set of embeddings and the second set of embeddings using a knowledge graph to determine whether the multimedia content or the access by the user violates the policy. The device may perform an action based on a result of processing the first set of embeddings and the second set of embeddings. The action may relate to the multimedia content or the access to the multimedia content by the user.

Abstract: Implementations are directed to providing categorization of transactional data, and include actions of providing a plurality of word embeddings based on domain-relevant text data, clustering word embeddings of the plurality of word embeddings into a plurality of clusters, receiving, in real-time, transactional data representative of a transaction, providing a category that is to be assigned to the transaction based on the transactional data, and the plurality of clusters, processing the category, the transactional data, the text data, and the plurality of clusters using a semantic search to provide reason text data, the reason text data representing a reason for selection of the category assigned to the transaction, and storing the transaction data, the category, and the reason text data in a transaction database.

Abstract: An identification and management system for log entries may filter historical data and generate closed log entries as a reference dataset. A dynamic learning engine may perform statistical modelling using the reference dataset to assign predetermined categories to each of a number of open log entries. An automation index may be generated for each of the open log entries. The automation index is indicative of accuracy of the assigned categories. Some of the open log entries may be identified as priority log entries which are representative of a group of the open log entries. The assigned category of the priority log entries may be analyzed for accuracy and the results of the analysis may be used to train the statistical model so that the open log entries may be iteratively assigned and re-assigned a category until the category of each open log entry reaches a desired accuracy.

Abstract: A device may receive multimedia data, metadata, and/or policy data. The device may process the policy data using a first set of techniques to determine a first set of embeddings for the policy data. The device may process the multimedia data or the metadata using a second set of techniques to determine a second set of embeddings for the multimedia data or the metadata. The device may process the first set of embeddings and the second set of embeddings using a knowledge graph to determine whether the multimedia content or the access by the user violates the policy. The device may perform an action based on a result of processing the first set of embeddings and the second set of embeddings. The action may relate to the multimedia content or the access to the multimedia content by the user.