Abstract: The present invention provides a system and method for managing operations in an enterprise application. The invention includes predicting a dataset characteristic such as an incident or outage in the enterprise application based on analysis of the dataset received from distinct data sources. The invention includes data cleansing, feature extraction based on probability data analysis and classification of dataset based on data models trained on historical dataset characteristic data. The invention includes linkedchain based architecture with configurable components structuring the enterprise application.

Abstract: Techniques are disclosed for automatically retraining a machine learning model based on the performance of this model falling below a performance threshold. In some embodiments, a computer system compares output of a new machine learning model for a new set of examples with known labels for examples in the new set of examples, wherein the new set of examples includes one or more new features. In some embodiments, the computer system determines, based on the comparing, whether a current performance of the new machine learning model satisfies a performance threshold for machine learning models, where the performance threshold is based on output of a benchmark machine learning model. In some embodiments, the computer system automatically triggers, in response to determining that the current performance of the new model does not satisfy the performance threshold, retraining of the new model.

Abstract: An apparatus for scheduling a data augmentation technique according to an embodiment includes a data set extractor, a first trainer, an operation extractor, a second trainer, and a schedule determinator. The apparatus may provide a schedule for a data augmentation technique capable of improving the performance of a neural network classification model in a shorter time compared to the related art.

Abstract: The present disclosure provides a quantum convolution operator, comprising: a quantum state encoding module, a quantum entanglement module, a quantum convolution kernel module, a measuring module, and a computing module; the quantum state encoding module is configured to encode a current group of input data onto qubits; the quantum entanglement module is configured to associate quantum state information of different qubits; the quantum convolution kernel module is configured to extract feature information corresponding to the quantum state information; the measuring module is configured to measure a quantum state of a preset qubit and obtain a corresponding amplitude; the computing module is configured to compute a convolution result corresponding to the current group of input data according to the measured quantum state and its amplitude.

Abstract: Embodiments of the present disclosure generally relate to methods for analyzing outcomes of illnesses, such as COVID-19, on living organisms. More particularly, embodiments of the present disclosure relate to methods for identifying risk of illness based on genetic markers and other available data, predicting results of mass exposure to an Illness based on a populations genomes and other available data, and providing indicators and methods of visualization for probability of illness in any living organism.

Abstract: A method for operating an artificial neuron and an apparatus for performing the method are provided. The artificial neuron may calculate a change amount of an activation based on an input signal received via an input synapse, determine whether an event occurs in response to the calculated change amount of the activation, and transmit, to an output synapse, an output signal that corresponds to the event in response to an occurrence of the event.

Abstract: A method, apparatus and product comprising: generating, by a first software compiler, an intermediate-level data structure based on a quantum program, the intermediate-level data structure is a Directed Acyclic Graph (DAG) that is a non-executable representation of the quantum program; initiating a first execution of the quantum program at the quantum execution platform by: obtaining, at a second software compiler, first real-time constraints on an availability of resources of the quantum execution platform for the first execution; generating, based on the first real-time constraints, a first quantum circuit that implements the DAG; and providing the first quantum circuit to the quantum execution platform to be executed thereon; and initiating a second execution of the quantum program at the quantum execution platform by: obtaining second real-time constraints on an availability of resources; generating a second quantum circuit; and providing the second quantum circuit to the quantum execution platform.

Abstract: One embodiment provides for a general-purpose graphics processing unit including a scheduler to schedule multiple matrix operations for execution by a general-purpose graphics processing unit. The multiple matrix operations are determined based on a single machine learning compute instruction. The single machine learning compute instruction is a convolution instruction and the multiple matrix operations are associated with a convolution operation.

Abstract: A computing server configured to process data of a domain from unstructured data sources to generate natural language phrases describing relationships between entities identified from the unstructured data. The computing server may receive master data schema and domain knowledge ontology of a domain including relationship definitions in the domain. The computing server may identify targeted types of named entities of the domain from the master data schema according to the relationship definitions in the domain knowledge ontology. The computing server may extract a plurality of named entities from unstructured data of the domain. The computing server may generate one or more sequences of named entities and assign entity labels to the named entities. The computing server may, based on the entity labels, generate natural language phrases describing relationships of sets of named entities.

Abstract: A method includes receiving, by a processor, an input data set. The input data set includes a plurality of features. The method includes determining, by the processor, one or more characteristics of the input data set. The method includes, based on the one or more characteristics, adjusting, by the processor, one or more architectural parameters of an automated model generation process. The automated model generation process is configured to generate a plurality of models using a weighted randomization process. The one or more architectural parameters weight the weighted randomization process to adjust a probability of generation of models having particular architectural features. The method further includes executing, by the processor, the automated model generation process to output a mode, the model including data representative of a neural network.

Abstract: A system for configuring and using a logical neural network including a graph syntax tree of formulae in a represented knowledgebase connected to each other via nodes representing each proposition. One neuron exists for each logical connective occurring in each formula and, additionally, one neuron for each unique proposition occurring in any formula. All neurons return pairs of values representing upper and lower bounds on truth values of their corresponding subformulae and propositions. Neurons corresponding to logical connectives accept as input the output of neurons corresponding to their operands and have activation functions configured to match the connectives' truth functions. Neurons corresponding to propositions accept as input the output of neurons established as proofs of bounds on the propositions' truth values and have activation functions configured to aggregate the tightest such bounds.

Abstract: A method and system for pruning a neural network (NN) block of a neural network during training, wherein the NN block comprises: a convolution operation configured to convolve an input feature map with a plurality of filters, each filter including a plurality of weights, to generate a plurality of filter outputs each corresponding to a respective filter; an activation operation configured to generate, for each of the filter outputs, a respective non-linearized output; a scaling operation configured to scale the non-linearized output generated in respect of each filter by multiplying the non-linearized output with a mask function and a respective scaling factor that corresponds to the filter.

Abstract: Data-dependent node-to-node knowledge sharing to increase the interpretability of the activation pattern of one or more nodes in a neural network, is implemented by a set of knowledge sharing links. Each link may comprise a knowledge providing node or other source P and a knowledge receiving node R. A knowledge sharing link can impose a node-specific regularization on the knowledge receiving node R to help guide the knowledge receiving node R to have an activation pattern that is more easily interpreted. The specification and training of the knowledge sharing links may be controlled by a cooperative human-AI learning supervisor system in which a human and an artificial intelligence system work cooperatively to improve the interpretability and performance of the client system.

Abstract: Described is a system and method for proactively determining and resolving events having low confidence scores and/or resolving disputed events. For example, when an event, such as a pick of an item from an inventory location within a materials handling facility occurs, the event aspects (e.g., user involved in the event, item involved in the event, action performed) are determined based on information provided from one or more input components (e.g., camera, weight sensor). If each event aspect cannot be determined with a high degree of confidence, the event information is provided to an associate for resolution.

Abstract: A device and a method for generating a compressed network from a trained neural network are provided. The method includes: a model generating a compressing map from first training data, the compressing map representing the impact of model components of the model to first output data in response to the first training data; generating a compressed network by compressing the trained neural network in accordance with the compressing map; the trained neural network generating trained network output data in response to second training data; the compressed network generating compressed network output data in response to the second training data; training the model by comparing the trained network output data with the compressed network output data.

Abstract: The invention relates to information representation, exchange, validation, and utilization. Embodiments of the invention enable a fully digital shared information reality: an information fabric, in which unlimited numbers of participants can all permanently access (with access controls) information objects that all participants can trust and verify, according to a universal set of protocols that are logically complete, address all stages of information exchange, and enable convincing, persuasive user experience. We disclose foundational embodiments that include methods to properly record, store, communicate and display information in digital form; computational verification and validation of information; and foundational concepts in human-information interaction. The invention teaches that by using unique digital objects, numerous difficulties and inefficiencies in state-of-the-art information exchange are overcome, and the next stage of digital transformation is enabled.

Abstract: A machine-learning based artificial intelligence device for finding an estimate of patent quality, such as patent lifetime or term is disclosed. Such a device may receive a first set of patent data and generate a list of binary classifiers. A candidate set of binary classifiers may be selected and using a heuristic search, for example an artificial neural network (ANN), a genetic algorithm, a final set of binary classifiers is found by maximizing iteratively a yield according to a cost function, such an area under a curve (AUC) of a receiver operating characteristic (ROC). The device may then receive patent information for a target patent and report an estimate of patent quality according to the final set of binary classifiers.

Abstract: Each of learning nodes calculates gradients of a loss function from an output result obtained by inputting learning data to a learning target neural network, converts a calculation result into a packet, and transmits the packet to a computing interconnect device. The computing interconnect device receives the packet transmitted from each of the learning nodes, acquires a value of the gradients stored in the packet, calculates a sum of the gradients, converts a calculation result into a packet, and transmits the packet to each of the learning nodes. Each of the learning nodes receives the packet transmitted from the computing interconnect device and updates a constituent parameter of a neural network based on a value stored in the packet.

Abstract: The disclosure herein provides methods, systems, and devices for measuring similarity of and generating recommendations for unique items. A recommendation system for generating recommendations of alternative unique items comprises an items information database, a penalty computation engine, a recommendation compilation engine, and one or more computers, wherein the penalty computation engine comprises a customizations filter, a condition filter, and a dissimilarity penalty calculator for determine the dissimilarity of attributes of alternative unique items from a plurality of selected items.

Abstract: A method for operating an artificial neuron and an apparatus for performing the method are provided. The artificial neuron may calculate a change amount of an activation based on an input signal received via an input synapse, determine whether an event occurs in response to the calculated change amount of the activation, and transmit, to an output synapse, an output signal that corresponds to the event in response to an occurrence of the event.