A novel and useful system and method of improved power performance and lowered memory requirements for an artificial neural network based on packing memory utilizing several structured sparsity mechanisms. The invention applies to neural network (NN) processing engines adapted to implement mechanisms to search for structured sparsity in weights and activations, resulting in a considerably reduced memory usage. The sparsity guided training mechanism synthesizes and generates structured sparsity weights. A compiler mechanism within a software development kit (SDK), manipulates structured weight domain sparsity to generate a sparse set of static weights for the NN. The structured sparsity static weights are loaded into the NN after compilation and utilized by both the structured weight domain sparsity mechanism and the structured activation domain sparsity mechanism. The application of structured sparsity lowers the span of search options and creates a relatively loose coupling between the data and control planes.

The present invention generally relates to system, method and graphical user interface for executing one or more tasks in dynamic data driven enterprise application. The invention includes creation of rules on a rule creation interface by one or more syntax from a rule creation syntax data library. The invention provides machine learning models driven rule engine for executing the tasks.

The present invention generally relates to system, method and graphical user interface for executing one or more tasks in dynamic data driven enterprise application. The invention includes creation of rules on a rule creation interface by one or more syntax from a rule creation syntax data library. The system of the invention is configured to identify optimum rule to process one or more tasks. The invention provides machine learning models driven rule engine for executing the tasks wherein an AI engine invokes dynamic conditions of the rules to execute the task.

Aspects relate to providing a counterfactual inference management technique capable of providing increased flexibility to allow users to select an appropriate counterfactual inference and offering scalability for handling tabular data and image data in a single configuration. A counterfactual inference management device comprising a classifier unit trained to determine whether a set of input data that includes a set of data features achieves a predetermined target and a counterfactual inference unit for generating a set of transformed data in which a subset of the set of data features are modified to counterfactual features. The classifier unit processes the set of transformed data to determine whether it achieves the predetermined target and calculates a counterfactual loss. The counterfactual inference unit is trained to reduce the counterfactual loss and generate a set of transformed data including counterfactual features that achieve the predetermined target.

Aspects relate to providing a counterfactual inference management technique capable of providing increased flexibility to allow users to select an appropriate counterfactual inference and offering scalability for handling tabular data and image data in a single configuration. A counterfactual inference management device comprising a classifier unit trained to determine whether a set of input data that includes a set of data features achieves a predetermined target and a counterfactual inference unit for generating a set of transformed data in which a subset of the set of data features are modified to counterfactual features. The classifier unit processes the set of transformed data to determine whether it achieves the predetermined target and calculates a counterfactual loss. The counterfactual inference unit is trained to reduce the counterfactual loss and generate a set of transformed data including counterfactual features that achieve the predetermined target.

Systems, computer-implemented methods, and computer program products to facilitate quantum platform routing of a quantum application component are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise a dissection component that identifies one or more components of a quantum application. The computer executable components can further comprise a determination component that selects at least one quantum platform to execute the one or more components of the quantum application based on a defined run criterion.

A method of configuring a smart booklet to encourage adherence to a treatment and/or educational program is disclosed, wherein the smart booklet is “off the grid” (e.g., not connected to an electrical or networking grid) and includes an integrated behavior incentivization feature. Based on an activation of a detection feature of the smart booklet, it is detected whether a state of one or more pages of the smart booklet has changed. Based on the determination that the state of the one or more pages has changed, a set of data items pertaining to the adherence to the treatment and/or educational program is created or updated. Based on an identification that the set of data items is indicative of a failure or a success with respect to the adherence to the treatment program, a message pertaining to the failure or the success is communicated via an output component of the smart booklet (e.g., to encourage the adherence to the treatment and/or educational program).

Neural network-based categorization can be improved by incorporating graph neural networks that operate on a graph representing the taxonomy of the categories into which a given input is to be categorized by the neural network based-categorization. The output of a graph neural network, operating on a graph representing the taxonomy of categories, can be combined with the output of a neural network operating upon the input to be categorized, such as through an interaction of multidimensional output data, such as a dot product of output vectors. In such a manner, information conveying the explicit relationships between categories, as defined by the taxonomy, can be incorporated into the categorization. To recapture information, incorporate new information, or reemphasize information a second neural network can also operate upon the input to be categorized, with the output of such a second neural network being merged with the output of the interaction.

Contiguous columns of a convolutional engine are partitioned into two or more groups. Each group of columns may be used to process input data. Filter weights assigned to one group may be distinct from filter weights assigned to another group.

Contiguous columns of a convolutional engine are partitioned into two or more groups. Each group of columns may be used to process input data. Filter weights assigned to one group may be distinct from filter weights assigned to another group.