Abstract: Systems and computer program products to perform an operation comprising: identifying a first attribute of a source code in a deep question answering system, computing an influence score for the first attribute based on a rule in the source code used to compute a confidence score for each of a plurality of candidate answers generated by the deep question answering system, computing an importance score for the first attribute based at least in part on the computed influence score, and upon determining that the importance score exceeds a predefined threshold, storing an indication that the first attribute is an important attribute relative to other attributes specified in the source code.

Abstract: Methods to perform an operation comprising: identifying a first attribute of a source code in a deep question answering system, computing an influence score for the first attribute based on a rule in the source code used to compute a confidence score for each of a plurality of candidate answers generated by the deep question answering system, computing an importance score for the first attribute based at least in part on the computed influence score, and upon determining that the importance score exceeds a predefined threshold, storing an indication that the first attribute is an important attribute relative to other attributes specified in the source code.

Abstract: An instructional design tool is provided for designing learning based applications. More specifically, the instructional design tool is configured to use captured expert knowledge for translating such knowledge into an environment used for instructional purposes. The instructional design tool includes at least one component configured to visually model a gaming scenario using recorded knowledge and graphical content defined by values associated with classes of respective models and translate the defined values into a standardized XML format.

Abstract: Embodiments of the invention relate to providing transposable access to a synapse array using a recursive array layout. One embodiment comprises maintaining synaptic weights for multiple synapses connecting multiple axons and multiple neurons, wherein the synaptic weights are maintained based on a recursive array layout. The recursive array layout facilitates transposable access to the synaptic weights. A neuronal spike event between an axon and a neuron is communicated via a corresponding connecting synapse by accessing the synaptic weight of the corresponding connecting synapse in the recursive array layout.

Abstract: Described is a system for dynamic background estimation which utilizes Particle Swarm Optimization (PSO). The present invention comprises a system, method, and computer program product for accurate estimation of a background mask corresponding to a dynamically changing scene. The system is configured to construct a background template model of a scene, and then capture an image of a current view of the scene with a camera. Thereafter, the system generates an image-based template matching cost function as an optimization problem, where the objective is to identify and fit a corresponding subregion of the background template model to the current camera view. The cost function is optimized using a PSO search algorithm. Finally, the system is configured to generate the corresponding subregion of the background template model for display. The inherent efficiency of PSO makes this system conducive for use in applications requiring real-time background estimation.

Abstract: Technical solutions are described for improving efficiency of training a resistive processing unit (RPU) array using a neural network training methodology. An example method includes reducing asymmetric RPUs from the RPU array by determining an asymmetric value of an RPU from the RPU array, and burning the RPU in response to the asymmetry value being above a predetermined threshold. The RPU can be burned by causing an electric voltage across the RPU to be above a predetermined limit. The method further includes initiating the training methodology for the RPU array after the asymmetric RPUs from the RPU array are reduced.

Abstract: Embodiments of the invention relate to canonical spiking neurons for spatiotemporal associative memory. An aspect of the invention provides a spatiotemporal associative memory including a plurality of electronic neurons having a layered neural net relationship with directional synaptic connectivity. The plurality of electronic neurons configured to detect the presence of a spatiotemporal pattern in a real-time data stream, and extract the spatiotemporal pattern. The plurality of electronic neurons are further configured to, based on learning rules, store the spatiotemporal pattern in the plurality of electronic neurons, and upon being presented with a version of the spatiotemporal pattern, retrieve the stored spatiotemporal pattern.

Abstract: Methods and systems for reducing finite element simulation time for acoustic response analysis are disclosed. In one embodiment, a method includes analytically creating a finite element model, the finite element model including a plurality of subdivisions. A plurality of cross-correlations between respective pairings of the subdivisions is then specified. A portion of the cross-correlations are then eliminated to provide a reduced set of cross-correlations between respective pairings of the subdivisions. The elimination includes determining a spatial distance value between at least two subdivisions, and discarding at least one of the cross-correlations for which the spatial distance value is greater than a specified threshold value. The finite element simulation is then performed using the reduced set of cross-correlations.

Abstract: A packet classification system, methods, and corresponding apparatus are provided for enabling packet classification. A processor of a security appliance coupled to a network uses a classifier table having a plurality of rules, the plurality of rules having at least one field, to build a decision tree structure including a plurality of nodes, the plurality of nodes including a subset of the plurality of rules. The plurality of nodes may be stride nodes, mask nodes, or a combination thereof. A mask node may remove restrictions of stride nodes, such as markers and consumption of contiguous bits. As long as a bit of a field is a non-consumed bit, the bit may be used for cutting a field in a mask node. An advantage of a mask node is that the mask node may consume fewer resources (e.g., memory) than a stride node.

Abstract: A method for predicting a patient's outcome variable, such as a probability of mortality/recovery, includes accessing at least one of a plurality past patients' data fields including physiological and/or laboratory data, and a time of stay indicating how long each patient had been under care at the time. An outcome variable estimation algorithm is generated by data mining from a plurality of past patients' physiological and/or laboratory data, corresponding time of stay, and associated outcome variables. A current patient's outcome variable is determined from the current patient's physiological and/or laboratory data, the current time of stay, and the outcome variable estimation algorithm.

Abstract: A method for detecting and responding to disturbances in a HVAC system using a noisy measurement signal and a signal filter is provided. The method includes detecting a deviation in the noisy measurement signal, resetting the filter in response to a detected deviation exceeding a noise threshold, filtering the noisy measurement signal using the signal filter to determine an estimated state value, and determining that a disturbance has occurred in response to the estimated state value crossing a disturbance threshold. In some embodiments, the method further includes performing one or more control actions in response to the detection of a disturbance.

Abstract: This NGDE algorithm incorporates a minimum cardinality candidate diagnosis generator which exploits conflict set reduction rules to dramatically reduce the search space and thus reduce the computational resources required to find minimum cardinality diagnoses.

Abstract: Embodiments of the invention relate to canonical spiking neurons for spatiotemporal associative memory. An aspect of the invention provides a spatiotemporal associative memory including a plurality of electronic neurons having a layered neural net relationship with directional synaptic connectivity. The plurality of electronic neurons configured to detect the presence of a spatiotemporal pattern in a real-time data stream, and extract the spatiotemporal pattern. The plurality of electronic neurons are further configured to, based on learning rules, store the spatiotemporal pattern in the plurality of electronic neurons, and upon being presented with a version of the spatiotemporal pattern, retrieve the stored spatiotemporal pattern.

Abstract: The current application is directed to an intelligent-thermostat-controlled environmental-conditioning system in which computational tasks and subcomponents with associated intelligent-thermostat functionalities are distributed to one or more of concealed and visible portions of one or more intelligent thermostats and, in certain implementations, to one or more intermediate boxes. The intelligent thermostats are interconnected to intermediate boxes by wired and/or wireless interfaces and intelligent thermostats intercommunicate with one another by wireless communications. Wireless communications include communications through a local router and an ISP, 3G and 4G wireless communications through a mobile service provider. Components of the intelligent-thermostat-controlled thermostat-controlled environmental-conditioning system may also be connected by wireless communications to remote computing facilities.

Abstract: A comfort controller in an HVAC system is provided. The comfort controller comprises a processor configured such that the comfort controller compares at least one of an actual run time of the HVAC system to a benchmark run time and an actual static pressure of the HVAC system to a benchmark static pressure. The processor is further configured such that, when at least one of the actual run time and the actual static pressure are outside a specified range of their associated benchmarks, the comfort controller determines that the HVAC system has an improper configuration. The processor is further configured such that the comfort controller displays the results of the comparison.

Abstract: In a substrate processing apparatus 1 which performs a process on a substrate W, each of multiple processing modules 2 includes at least a first processing member 21 and a second processing member 22, and substrate transfer devices 15 and 17 transfer substrates W into the multiple processing modules 2. Further, a controller 3 configured to control the substrate processing apparatus 1 stores member operating possibility information on whether it is possible to use the first processing member 21 and the second processing member 22 provided in each of the multiple processing modules 2, and the controller 3 creates, based on the member operating possibility information and process recipe information on processes to be performed on the substrates W, a transfer schedule in which the substrate transfer devices 15 and 17 transfer the substrates W into the multiple processing modules 2 in parallel.

Abstract: A system and method for switch management includes a switch including a plurality of switch modules, and a status display panel. The plurality of switch modules includes one or more power supply modules for providing power to the switch, one or more cooling modules for cooling the switch, and one or more switching modules. The switch is configured to detect the plurality of switch modules, interrogate the detected switch modules, hierarchically organize status information based on information associated with the interrogated switch modules, and display the organized status information on the status display panel. The status information is displayed on the status display panel using an interactive status display system. In some examples, the switch further includes a plurality of status indicators, and the switch is further configured to temporarily activate the status indicators in response to active use of the status display system.

Abstract: Mechanisms for predicting a GC duration are described herein. In one embodiment, the mechanisms include receiving a first set of features determined based on current operating status and prior garbage collection (GC) statistics of a first storage system. In one embodiment, the mechanisms include predicting a GC duration of a first GC process being performed at the first storage system by applying a predictive model on the first set of features, wherein the predictive model was generated based on a second set of features received periodically from a plurality of storage systems.

Abstract: The invention involves generating and presenting, typically electronically, a number of design alternatives to persons who are participating in the design, selection, or market research exercise. The participants (referred to as “selectors”) transmit data indicative of their preferences among or between the presented design alternatives, and that data is used to derive a new generation of design alternatives or proposals. The new designs are generated through the use of a computer program exploiting a genetic or evolutionary computational technique. The process is repeated, typically for many iterations or cycles.

Abstract: An adaptive interface for a programmable system, for predicting a desired user function, based on user history, as well as machine internal status and context. The apparatus receives an input from the user and other data. A predicted input is presented for confirmation by the user, and the predictive mechanism is updated based on this feedback. Also provided is a pattern recognition system for a multimedia device, wherein a user input is matched to a video stream on a conceptual basis, allowing inexact programming of a multimedia device. The system analyzes a data stream for correspondence with a data pattern for processing and storage. The data stream is subjected to adaptive pattern recognition to extract features of interest to provide a highly compressed representation which may be efficiently processed to determine correspondence.