A method for performing contrastive learning for graph tasks and datasets by employing an information-aware graph contrastive learning framework is presented. The method includes obtaining two semantically similar views of a graph coupled with a label for training by employing a view augmentation component, feeding the two semantically similar views into respective encoder networks to extract latent representations preserving both structure and attribute information in the two views, optimizing a contrastive loss based on a contrastive mode by maximizing feature consistency between the latent representations, training a neural network with the optimized contrastive loss, and predicting a new graph label or a new node label in the graph.

Aspects of the disclosure relate to design as a service for configuring custom software. A computing platform may receive natural language input from a user specifying a software customization request. The computing platform may convert the natural language input into a visual output corresponding to the software customization request. The computing platform may send the visual output to a user interface. The computing platform may receive a modification request from the user specifying, using natural language, one or more modifications to the visual output. The computing platform may modify, using natural language processing, the visual output based on the modification request. The computing platform may log the one or more modifications to the visual output in a tracking log. The computing platform may send the modified visual output to the user interface.

A system, method and computer program product for integrated management of animate and inanimate objects of an enterprise, including a cloud-based server having a database, a website, and configured for running computer programs thereon; a user device including a smartphone, tablet and/or personal computer (PC) running an application or software including a gamified user interface (UI) configured to connect to the database and function as a data entry and display device; automated devices including a sensor, electronic switch, pump and/or a hydroponic dosing device connected to the database and configured to collect and transmit data or to react to received commands; an Artificial Intelligence (AI) powered engine configured to monitor statuses of animate and inanimate objects of an enterprise, as well as external conditions and actors that affect the enterprise, and based on analysis of the statuses, configured to task employees and/or the automated devices of the enterprise, and configured to employ cognitive reasoning to provide the enterprise with advice on managing business operations; and a framework employed by the AI engine based on a metaphor of a novel, with business operations of the enterprise presented as a story, and including a data model that follows rules of grammar.

Systems and methods for recording information at a granular level; checking and verifying that data is used and processed is consistent with an entity's internal policies and/or external regulations; and producing reports to authorized users (e.g., individuals and organizations) with information are provided. The system and methods capture required data in an immutable fashion so that users outside of an entity (e.g., public, third parties) can check and audit that internal policies and other regulatory policies and frameworks are followed.

Embodiments are directed to a method of performing autonomous learning for updating input features used for an artificial intelligence model, the method comprising receiving updated data of an information space that includes a graph of nodes having a defined topology, the updated data including historical data of requests to the artificial intelligence model and output results associated with the requests, wherein different categories of input data corresponds to different input nodes of the graph. The method may further comprise updating edge connections between the nodes of the graph by performing path optimizations that each use a set of agents to explore the information space over cycles to reduce a cost function, each connection including a strength value, wherein during each path optimization, path information is shared between the rest of agents at each cycle for determining a next position value for each of the set of agents in the graph.

Systems and methods for device type classification system include a rules engine and a machine learning engine. The machine learning engine can be trained using device type data from multiple networks. The machine learning engine and the rules engine can receive data for devices on a network at a first point in time. The data can be submitted to a rules engine and the machine learning engine, which each produce device type probabilities for devices on the network. The device type probabilities from the rules engine and the machine learning engine can be processed to determine device types for one or more devices on the network. As more data becomes available at later points in time, the additional data can be provided to the rules engine and the machine learning engine to update the device type determinations for the network.

In an embodiment, a computer-implemented method elicits intents of agents in a social network with imperfect information. In the method, data representing the social network is gathered. The social network includes a plurality of resources and a plurality of agents seeking to alter values of the resources. In an example, the resources may be artists, and the agents may be art institutions. The social network is represented as a graph including nodes representing the plurality of agents. The nodes are connected by edges specifying how resources are transferred between the agents. Based at least in part on the graph, an affinity value and a trajectory value between respective agents in the plurality of agents is determined. Based at least in part on the graph, the affinity value and the trajectory value are input into a trained machine learning model to identify a strategy of the plurality of agents.

There is a need for faster and more accurate predictive data analysis steps/operations. This need can be addressed by, for example, techniques for efficient predictive data analysis steps/operations. In one example, a method includes identifying a first predictive entity embedding for the first predictive entity and a second predictive entity embedding for a second predictive entity; determining, using a similarity determination machine learning model and based at least in part on the first predictive entity embedding and the second predictive entity embedding, a predicted cross-entity similarity measure; and performing one or more prediction-based actions based at least in part on the predicted cross-entity similarity measure.

A system, method and non-transitory computer readable medium for editing images with verbal commands are described. Embodiments of the system, method and non-transitory computer readable medium may include an artificial neural network (ANN) comprising a word embedding component configured to convert text input into a set of word vectors, a feature encoder configured to create a combined feature vector for the text input based on the word vectors, a scoring layer configured to compute labeling scores based on the combined feature vectors, wherein the feature encoder, the scoring layer, or both are trained using multi-task learning with a loss function including a first loss value and an additional loss value based on mutual information, context-based prediction, or sentence-based prediction, and a command component configured to identify a set of image editing word labels based on the labeling scores.

Devices and techniques are generally described for sending a first instruction for a device to output first content while the speech-processing device is in an ambient state during a first time period. First feedback data is received indicating that a first action associated with the first content was requested at a first time. A determination is made that the first time is during the first time period. Timing data related to a current time of the device is determined. Second content is determined based at least in part on the first action being requested during the first time period and the timing data. A second instruction is sent effective to cause the device to output second content while in the ambient state during a second time period.