Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for computing a layer output for a convolutional neural network layer, the method comprising: receiving a plurality of activation inputs; forming a plurality of vector inputs from the plurality of activation inputs, each vector input comprising values from a distinct region within the multi-dimensional matrix; sending the plurality of vector inputs to one or more cells along a first dimension of the systolic array; generating a plurality of rotated kernel structures from each of the plurality of kernel; sending each kernel structure and each rotated kernel structure to one or more cells along a second dimension of the systolic array; causing the systolic array to generate an accumulated output based on the plurality of value inputs and the plurality of kernels; and generating the layer output from the accumulated output.

Abstract: An approach is provided for providing predictive classification of actionable network alerts. The approach includes receiving the plurality of alerts. Each alert of the plurality of alerts indicates an alarm condition occurring at a monitored network system, and is a data record comprising one or more data fields describing the alarm condition. The approach also includes classifying said each alert using a predictive machine learning model. The predictive machine learning model is trained to classify said each alert as actionable or non-actionable using the one or more data fields of said each alert as one or more respective classification features, and to calculate a respective probability that said each alert is actionable or non-actionable. The approach further includes presenting the plurality of alerts in a network monitoring user interface based on the respective probability of said each alert.

Abstract: A system, method, and computer program product are provided for generating intelligent automated adaptive decisions. In operation, a system receives a request to generate a prediction associated with a business problem for a customer. The system identifies a customer segment from a plurality of customer segments to which the new customer is most closely associated. Additionally, the system identifies a statistical model associated with the customer segment. Moreover, the system selects a best prediction from a competing set of machine learning models and the statistical model, utilizing a multi arm bandit arbitrator applying a multi arm bandit technique to solve the business problem.

Abstract: The present disclosure relates to processing support data to increase a self-support knowledge base. In some embodiments, assisted support data is received comprising a record of an interaction between a user and a support professional. In certain embodiments, a support data set is extracted from the assisted support data. In some embodiments, feedback related to the support data set is received. The feedback may include an indication that the support data set is ready to be included in the self-support knowledge base. In some embodiments, upon determining, based on the feedback, that the support data set is ready to be used for self-support, the support data set is added to the self-support knowledge base. The self-support knowledge base may be accessible by a plurality of users.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to receive a plurality of data inputs for training a neural network, wherein the data inputs comprise training data and weights inputs; represent the data inputs in a first form; and represent the weight inputs in a second form. Other embodiments are also disclosed and claimed.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for organizing trained and untrained neural networks. In one aspect, a neural network device includes a collection of node assemblies interconnected by between-assembly links, each node assembly itself comprising a network of nodes interconnected by a plurality of within-assembly links, wherein each of the between-assembly links and the within-assembly links have an associated weight, each weight embodying a strength of connection between the nodes joined by the associated link, the nodes within each assembly being more likely to be connected to other nodes within that assembly than to be connected to nodes within others of the node assemblies.

Abstract: In various embodiments, a natural language (NL) application implements functionality that enables users to more effectively access various data storage systems based on NL requests. As described, the operations of the NL application are guided by, at least in part, on one or more templates and/or machine-learning models. Advantageously, the templates and/or machine-learning models provide a flexible framework that may be readily tailored to reduce the amount of time and user effort associated with processing NL requests and to increase the overall accuracy of NL application implementations.

Abstract: Methods may include defining operational parameters for an initial composition design; generating an initial composition design from the defined operational parameters; predicting the performance of the initial composition design using a statistical model; comparing the performance of the initial composition design with the operational parameters; optimizing the initial composition design according to the defined operational parameters; and outputting a final composition design. Methods may also include defining operational parameters for an initial composition design for a wellbore fluid; generating an initial composition design from the defined operational parameters; predicting the performance of the initial composition design using a statistical model; comparing the performance of the initial composition design with the operational parameters; optimizing the initial composition design according to the defined operational parameters; and outputting a final composition design.

Abstract: Embodiments herein implement quantum annealing with a driver Hamiltonian that uses oscillating fields to advantageously obtain a quantum speedup over classical computing techniques. For a many-body quantum system formed with qubits, the oscillating fields drive the qubits so as to independently modulate the magnitudes and/or directions of transverse terms of the driver Hamiltonian. In particular, embodiments provide a quantum speedup for two types of first-order phase transitions: the paramagnet-to-spin-glass transition, and transitions between distinct “bit string” states. The resulting speedup is robust against energy fluctuations (e.g., 1/f noise), in contrast to other strategies like variable-rate annealing. Each oscillating field may be an oscillating electric field or magnetic field. The oscillating fields can be implemented with superconducting flux qubits by coupling oscillating fluxes and/or voltages to the flux qubits.

Abstract: In an example, an apparatus comprises a plurality of execution units comprising and logic, at least partially including hardware logic, to receive a plurality of data inputs for training a neural network, wherein the data inputs comprise training data and weights inputs; represent the data inputs in a first form; and represent the weight inputs in a second form. Other embodiments are also disclosed and claimed.

Abstract: Systems and methods for using collecting and analyzing device sensor data to determine whether an individual is an operator or a passenger of a vehicle are disclosed. According to certain aspects, an electronic device associated with the individual may collect or access sensor data that is indicative of or associated with an operation of the vehicle. The electronic device may transmit pertinent portion(s) of the sensor data to a backend server, which may input the portion(s) into a neural network for analysis. The neural network may output a probability metric(s) indicative of whether the individual is a passenger or an operator of the vehicle.

Abstract: A generic online, probabilistic, approximate computational inference model for learning-based data processing is presented. The model includes detection, feature production and classification steps. It employs Bayesian Probabilistic Models (BPMs) to characterize complex real-world behaviors under uncertainty. The BPM learning is incremental. Online learning enables BPM adaptation to new data. The available data drives BPM complexity (e.g., number of states) accommodating spatial and temporal ambiguities, occlusions, environmental clutter, and large inter-domain data variability. Generic Sequential Bayesian Inference (GSBI) efficiently operates over BPMs to process streaming or forensic data. Deep Belief Networks (DBNs) learn feature representations from data. Examples include model applications for streaming imagery (e.g., video) and automatic target recognition (ATR).

Abstract: Detecting patterns and sequences associated with an anomaly in predictions made a predictive system. The predictive system makes predictions by learning spatial patterns and temporal sequences in an input data that change over time. As the input data is received, the predictive system generates a series of predictions based on the input data. Each prediction is compared with corresponding actual value or state. If the prediction does not match or deviates significantly from the actual value or state, an anomaly is identified for further analysis. A corresponding state or a series of states of the predictive system before or at the time of prediction are associated with the anomaly and stored. The anomaly can be detected by monitoring whether the predictive system is placed in the state or states that is the same or similar to the stored state or states.

Abstract: A method for performing multi-label classification includes extracting a feature vector from an input vector including input data by a feature extractor, determining, by a label predictor, a relevant vector including relevant labels having relevant scores based on the feature vector, updating a binary masking vector by masking pre-selected labels having been selected in previous label selections, applying the updated binary masking vector to the relevant vector such that the relevant label vector is updated to exclude the pre-selected labels from the relevant labels, and selecting a relevant label from the updated relevant label vector based on the relevant scores of the updated relevant label vector.

Abstract: Systems and methods for augmenting incomplete training dataset for use in a machine learning system are described herein. In an embodiment, a server computer receives a plurality of input training datasets including one or more incomplete input training datasets and one or more complete datasets which contain one or more failure training datasets, the incomplete input training datasets comprising a plurality of parameters. Using the one or more failure training datasets, the server computer generates temporal failure data describing a likelihood of failure of an item as a function of time. Using the one or more complete training datasets, the server computer generates parameter specific likelihoods of failure of an item. The server computer augments the one or more incomplete input training datasets using the temporal failure data and/or the parameter specific likelihoods of failure to create one or more augmented training datasets.

Abstract: A system for generating digital models of nitrogen availability based on field data, weather forecast data, and models of water flow, temperature, and crop uptake of nitrogen and water is provided. In an embodiment, field data and forecast data are received by an agricultural intelligence computing system. Based on the received data, the agricultural intelligence computing system models changes in temperature of different soil layers, moisture content of different soil layers, and loss of nitrogen and water to the soil through crop uptake, leaching, denitrification, volatilization, and evapotranspiration. The agricultural intelligence computing system creates a digital model of nitrogen availability based on the temperature, moisture content, and loss models.

Abstract: A computer solves a nonlinear optimization problem. An optimality check is performed for a current solution to an objective function that is a nonlinear equation with constraint functions on decision variables. When the performed optimality check indicates that the current solution is not an optimal solution, a barrier parameter value is updated, and a Lagrange multiplier value is updated for each constraint function based on a result of a complementarity slackness test. The current solution to the objective function is updated using a search direction vector determined by solving a primal-dual linear system that includes a dual variable for each constraint function and a step length value determined for each decision variable and for each dual variable. The operations are repeated until the optimality check indicates that the current solution is the optimal solution or a predefined number of iterations has been performed.

Abstract: We describe a method of reinforcement learning for a subject system having multiple states and actions to move from one state to the next. Training data is generated by operating on the system with a succession of actions and used to train a second neural network. Target values for training the second neural network are derived from a first neural network which is generated by copying weights of the second neural network at intervals.

Abstract: According to exemplary embodiments, a method, processor, and system for accelerating a recurrent neural network are presented. A method of accelerating a recurrent neural network may include distributing from a first master core to each of a plurality of processing cores a same relative one or more columns of weight matrix data for each of a plurality of gates in the neural network, broadcasting a current input vector from the first master core to each of the processing cores, and processing each column of weight matrix data in parallel, at each of the respective processing cores.

Abstract: A system for guiding and evaluating physical positioning, orientation and motion of the human body, comprising: a cloud computing-based subsystem including an artificial neural network and spatial position analyzer said cloud computing-based subsystem adapted for data storage, management and analysis; at least one motion sensing device wearable on the human body, said at least one motion sensing device adapted to detect changes in at least one of spatial position, orientation, and rate of motion; a mobile subsystem running an application program (app) that controls said at least one motion sensing device, said mobile subsystem adapted to capture activity data quantifying said changes in at least one of spatial position, orientation, and rate of motion, said mobile subsystem further adapted to transfer said activity data to said cloud computing-based subsystem, wherein said cloud computing-based subsystem processes, stores, and analyzes said activity data.