Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media that support machine learning-based application management for enterprise systems. The aspects described herein enable resource and time-efficient scheduling of training anomaly detection models (e.g., machine learning (ML) models) corresponding to the applications based on log data generated by the applications. Aspects also provide integration of the trained anomaly detection models with an application dependency graph to enable prediction of application failures based on detected anomalies and relationships between applications determined from the application dependency graph. Further aspects leverage this integration to output reasons associated with predicted application failures and to provide recommended recovery actions to be performed to recover from the predicted application failures. Other aspects and features are also described.

Abstract: In some implementations, an olfaction system may receive partition coefficients associated with one or more molecules detected in a headspace of a sample captured from an environment. The olfaction system may generate a quantum-ready dataset based on the partition coefficients using a partial quantum autoencoder that includes one or more quantum gate layers. The olfaction system may use a quantum approximate optimization algorithm to identify, within a spectrum of potential smells simulated by a quantum circuit, a set of smells emitted by the sample based on the quantum-ready dataset. The olfaction system may map a set of objects to the set of smells emitted by the sample. The olfaction system may predict a future state associated with the set of smells emitted by the sample using one or more hybrid quantum machine learning models.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media facilitating automated apparel design using deep learning techniques. For example, user instructions may be received as text data (or converted to text data from audio data representing user speech), and natural language processing (NLP) may be performed on the text data to interpret the user instructions. An apparel design may be generated in real-time/substantially real-time based on the user instructions. For example, the interpreted user instructions may be provided as input to at least one machine learning (ML) model that is configured to determine one or more visual apparel elements based on the user instructions and to generate the apparel design based on the visual apparel elements. One or more operations may be initiated based on the apparel design.

Abstract: Aspects of the present disclosure provide systems, methods, and computer-readable storage media facilitating automated apparel design using deep learning techniques. For example, user instructions may be received as text data (or converted to text data from audio data representing user speech), and natural language processing (NLP) may be performed on the text data to interpret the user instructions. An apparel design may be generated in real-time/substantially real-time based on the user instructions. For example, the interpreted user instructions may be provided as input to at least one machine learning (ML) model that is configured to determine one or more visual apparel elements based on the user instructions and to generate the apparel design based on the visual apparel elements. One or more operations may be initiated based on the apparel design.

Abstract: A system and method for modifying existing rules of an existing anti-money laundering software system to reduce false alerts is disclosed. The system and method can find relationships amongst transactions and actors involved in transactions by using knowledge graphs and techniques that can help determine actors' likelihood of money laundering. Artificial intelligence may be used to: augment missing data at various stages throughout the disclosed method, help find new thresholds for existing rules of an anti-money laundering system, and test the new thresholds before making recommendations for thresholds. The system and method can gather more context about transactions and actors (e.g., account holders) by providing a way for entities, such as financial institutions, to share transaction data, non-transaction data, analyses based on transaction data, and historical alerts through private blockchain.

Abstract: Examples of a multisource augmented reality model are defined. In an example, the system receives a query from a user. The system obtains representative data corresponding to an environment associated with the query and identifies at least one context therein. The system obtains product parameter data and identifies a parameter set therein to process the query. The system implements an artificial intelligence component to sort the product parameter data, the representative data, and the context for identifying pertinent data domains associated with the query. The system may establish a product augmented reality model corresponding to the product by performing a first cognitive learning operation on a domain from the updated pertinent data domains and the identified parameter set. The system may a list of related products for guided selling facilitating a shopping decision of the user. The system may generate an augmented reality result for the user.