Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing intent sensitive search results. In one aspect, a method includes receiving a current query for a current search session that is associated with a user identifier. One or more potential refinements for the current query are identified, each potential refinement being one or more terms and based on previous queries associated with the user identifier and previous queries associated with other user identifiers. One or more secondary queries are generated, each secondary query including the current query and one of the potential refinements, each secondary query matching a query-refinement pair in a trigger map that includes a plurality of query-refinement pairs. Secondary search results are identified for the secondary queries. Search results are provided including at least one of the secondary search results.

Abstract: According to one embodiment, a visual detection system includes an image processing unit coupled to a display and one or more neuro-physiological sensors. The display generates an image that may be viewed by a user. The neuro-physiological sensors generate neuro-physiological signals representing neuro-physiological characteristics of the user while viewing the display. The image processing unit receives the neuro-physiological signals from the neuro-physiological sensors, determines a region of interest in the image according to the neuro-physiological signals, and provides an indication of the presence of the region of interest in the image.

Abstract: Embodiments of the disclosure can include systems and methods for facilitating communication between a point of sale device and a consumer device. In one embodiment, a computer-implemented method for communicating with a consumer device at a point of sale (POS) can be provided. The method can include establishing, by a merchant POS device, communication with the consumer device at the point of sale; collecting, by the merchant POS device, transaction-related information from a payment application associated with the consumer device; determining, by the merchant POS device, that the collected transaction-related information does not include both payment-related information and value added services (VAS) information associated with one or more VAS; and collecting, by the merchant POS device based at least in part upon the determination, second transaction-related information from a second payment application associated with the consumer device.

Abstract: A production planning system for allocating production capacity to meet a demand includes an operational module and a simulating module. The operational module is for receiving demand inputs, calculating a consolidated demand based on the demand inputs, calculating and storing a production capacity, and creating a production plan. The simulating module includes a data retriever, a simulated data handler, and a simulating planner. The data retriever is for retrieving and storing consolidated demand and capacity data from the at least one operational processor. The simulated data handler is for receiving a simulated demand input and creating a simulated consolidated demand by adding the simulated demand input to the retrieved consolidated demand. The simulating planner is for creating a simulated production plan based on the simulated consolidated demand.

Abstract: Embodiments of the present invention provide a method and device for synthesis of network traffic. The method includes extracting a first real traffic composition parameter sequence and a second real traffic composition parameter sequence from real traffic. A first synthetic traffic composition parameter sequence is generated. Relational coefficients between first traffic composition parameters and second traffic composition parameters are obtained. A second synthetic traffic composition parameter sequence is generated and synthetic traffic is generated according to the first synthetic traffic composition parameter sequence and the second synthetic traffic composition parameter sequence.

Abstract: Neuronal networks of electronic neurons interconnected via electronic synapses with synaptic weight normalization. The synaptic weights are based on learning rules for the neuronal network, such that a synaptic weight for a synapse determines the effect of a spiking source neuron on a target neuron connected via the synapse. Each synaptic weight is maintained within a predetermined range by performing synaptic weight normalization for neural network stability.

Abstract: This application discloses a neural network that also functions as a connection oriented packet data network using an MPLS-type label switching technology. The neural network uses its intelligence to build and manage label switched paths (LSPs) to transport user packets and solve complex mathematical problems. However, the methods taught here can be applied to other data networks including ad-hoc, mobile, and traditional packet networks, cell or frame-switched networks, time-slot networks and the like.

Abstract: Efficient updates of connections in artificial neuron networks may be implemented. A framework may be used to describe the connections using a linear synaptic dynamic process, characterized by stable equilibrium. The state of neurons and synapses within the network may be updated, based on inputs and outputs to/from neurons. In some implementations, the updates may be implemented at regular time intervals. In one or more implementations, the updates may be implemented on-demand, based on the network activity (e.g., neuron output and/or input) so as to further reduce computational load associated with the synaptic updates. The connection updates may be decomposed into multiple event-dependent connection change components that may be used to describe connection plasticity change due to neuron input. Using event-dependent connection change components, connection updates may be executed on per neuron basis, as opposed to per-connection basis.

Abstract: A neural processing engine may perform processing within a neural processing system and/or artificial neural network. The neural processing engine may be configured to effectively and efficiently perform the type of processing required in implementing a neural processing system and/or an artificial neural network. This configuration may facilitate such processing with neural processing engines having an enhanced computational density and/or processor density with respect to conventional processing units.

Abstract: A spike domain asynchronous neuron circuit includes a first spike to exponential circuit for emulating kinetic dynamics at a neuron input and converting voltage spikes into exponentials, a first adjustable gain circuit for emulating homeostatic plasticity coupled to the first voltage-type spike exponential output and having a first current output, a neuron core circuit coupled to the first current output for emulating a neuron core and having a spike encoded voltage output, a filter and comparator circuit coupled to the spike encoded voltage output and having a gain control output coupled to the first adjustable gain circuit for controlling a gain of the first adjustable gain circuit, and an adjustable delay circuit for emulating an axonal delay coupled to the spike encoded voltage output and having an axonal delay output.

Abstract: Generalized state-dependent learning framework in artificial neuron networks may be implemented. A framework may be used to describe plasticity updates of neuron connections based on connection state term and neuron state term. The state connections within the network may be updated based on inputs and outputs to/from neurons. The input connections of a neuron may be updated using connection traces comprising a time-history of inputs provided via the connections. Weights of the connections may be updated and connection state may be time varying. The updated weights may be determined using a rate of change of the trace and a term comprising a product of a per-neuron contribution and a per-connection contribution configured to account for the state time-dependency. Using event-dependent connection change components, connection updates may be executed on per neuron basis, as opposed to per-connection basis.

Abstract: In one embodiment, when a computing system is in a first state, a first set of inputs from one or more first sensors is detected. A first sensor value array is generated, and the first value array is fed as input to a first function generated by a first neural network. One or more first output values are calculated based on the first function, and a determination is made based on these first output values if a first action has occurred. If a first action has occurred, a second sensor value array is generated from a second set of inputs from one or more second sensors. The second sensor value array is fed as input to a second function generated by a second neural network. One or more second output values are calculated based on the second function, and the first state is exited based on these second output values.

Abstract: Apparatus and methods for conditional plasticity in a neural network. In one approach, conditional plasticity mechanism is configured to select alternate plasticity rules when performing connection updates. The selection mechanism is adapted based on a comparison of actual connection efficiency and target efficiency. For instance, when actual efficiency is below the target value, the STDP rule may be modulated to increase long term potentiation. Similarly, when actual efficiency is above the target value, the STDP rule may be modulated to increase long term connection depression. The conditional plasticity mechanism dynamically adjusts connection efficacy, and prevents uncontrolled increase of connection weights, thereby improving network operation when processing information of a varying nature.

Abstract: In one embodiment, the present invention provides a neural network comprising multiple modalities. Each modality comprises multiple neurons. The neural network further comprises an interconnection lattice for cross-associating signaling between the neurons in different modalities. The interconnection lattice includes a plurality of perception neuron populations along a number of bottom-up signaling pathways, and a plurality of action neuron populations along a number of top-down signaling pathways. Each perception neuron along a bottom-up signaling pathway has a corresponding action neuron along a reciprocal top-down signaling pathway. An input neuron population configured to receive sensory input drives perception neurons along a number of bottom-up signaling pathways. A first set of perception neurons along bottom-up signaling pathways drive a first set of action neurons along top-down signaling pathways.

Abstract: A system, method, and computer program product are provided for efficient allocation of attributes corresponding to neurons or connections of multiple types using a common data structure. A map file is generated by a pre-processor in order to map an attribute of a neuron or connection to a particular location within the common data structure based on a type associated with the neuron or connection, while allowing a neuron or connection of a different type to map its own attribute to that same particular location. Additionally, kernel code can be written to reference attribute names made available by the map file in order to provide reusability of code.

Abstract: In one embodiment, first weight information indicating a first set of delta values is obtained, where the first set of delta values includes a first delta value for each weight in a set of weights, the set of weights including a weight for each of a set of one or more parameters of a model. In addition, second weight information indicating a second set of delta values is obtained, where the second set of delta values includes a second delta value for each weight in the set of weights. Combined weight information including a combined set of delta values or a combined set of weights is generated based, at least in part, upon the first weight information and the second weight information.

Abstract: An apparatus for generating event detection rules in a multiple-component computer system in accordance with embodiments of the invention may include a configuration information-extracting section for acquiring system configuration information from a multiple-component computer system. The system configuration information may include related information that describes relationships among system components. The apparatus may further include a history information-collecting section for collecting history information from the multiple-component computer system, such as log information and/or failure information output from a component upon a system failure. A candidate event-identifying section may identify candidate events that may be selected by a user to generate a detection rule based on the system configuration information and the history information. Finally, a candidate event-presenting section may present the candidate events to a user for selection.

Abstract: A method and apparatus for detection of relationships between objects in a meta-model semantic network is described. Semantic objects and semantic relations of a meta-model of business objects are generated from a meta-model semantic network. The semantic relations are based on connections between the semantic objects. A probability model of terminology usage in the semantic objects and the semantic relations is generated. A neural network is formed based on usage of the semantic objects, the semantic relations, and the probability model. The neural network is integrated with the semantic objects, the semantic relations, and the probability model to generate a contextual network. The generated probability model is integrated with semantic objects and neural networks for form parallel networks.

Abstract: Generalized learning rules may be implemented. A framework may be used to enable adaptive spiking neuron signal processing system to flexibly combine different learning rules (supervised, unsupervised, reinforcement learning) with different methods (online or batch learning). The generalized learning framework may employ time-averaged performance function as the learning measure thereby enabling modular architecture where learning tasks are separated from control tasks, so that changes in one of the modules do not necessitate changes within the other. Separation of learning tasks from the control tasks implementations may allow dynamic reconfiguration of the learning block in response to a task change or learning method change in real time. The generalized spiking neuron learning apparatus may be capable of implementing several learning rules concurrently based on the desired control application and without requiring users to explicitly identify the required learning rule composition for that task.

Abstract: Certain aspects of the present disclosure provide methods and apparatus for a continuous-time neural network event-based simulation. This model is flexible, has rich behavioral options, can be solved directly, and is low complexity. One example method generally includes determining a first state of a neuron model at or shortly after a first event, wherein the neuron model has a closed-form solution in continuous time; and determining a second state of the neuron model at or shortly after a second event, based on the first state. Dynamics of the first and second states are coupled to the neuron model only at the first and second events, respectively, and are decoupled between the first and second events.

Abstract: A learning and decoding technique is provided for a neural network. The technique involves using a set of neurons, referred to as beacons, wherein said beacons are binary neurons capable of assuming only two states, an on state and an off state. The beacons are distributed in blocks of a predetermined number of beacons and being allocated for processing a sub-message. Each beacon is associated with a specific occurrence of the sub-message. Learning includes splitting a message into B sub-messages to be learned, where B is greater than or equal to two; activating, for a sub-message, a single beacon in each block to be in the on state, all of the other beacons of the block being in the off state; and activating binary connections between the on beacons of each of the block for a message to be learned, which assume only connected and disconnected states.

Abstract: Techniques for reconstructing a signal encoded with a time encoding machine (TEM) using a recurrent neural network including receiving a TEM-encoded signal, processing the TEM-encoded signal, and reconstructing the TEM-encoded signal with a recurrent neural network.

Abstract: A method for implementing a reservoir simulator is described. The method comprises developing training data by performing a calculation on an initial set of input data relating to reservoir conditions to obtain corresponding output data; training an artificial neural network (“ANN”) to perform the calculation using the training data; and using the trained ANN to perform the calculation on a second set of input data to obtain corresponding output data for use by the reservoir simulator in performing simulations.

Abstract: Certain aspects of the present disclosure support a technique for strategic synaptic failure and learning in spiking neural networks. A synaptic weight for a synaptic connection between a pre-synaptic neuron and a post-synaptic neuron can be first determined (e.g., according to a learning rule). Then, one or more failures of the synaptic connection can be determined based on a set of characteristics of the synaptic connection. The one or more failures can be omitted from computation of a neuronal behavior of the post-synaptic neuron.

Abstract: A mobile station is arranged to determine its location, which is searched against street addresses from a database, and at least one matching street address is retrieved. The street address is searched on the mobile station and/or over the network. The search engine conducts a search in the mobile station file system and/or the Internet and/or a file system over the network with the at least one query term, —at least one search result is arranged to be displayed to user on the screen of the mobile station. This facilitates on-demand effortless Mobile Internet Search that allows the users to access opportunities that they did not know about, or would not have had time to find out about with minimum effort as the software of the mobile phone is scanning the Internet and information pages for these opportunities and displaying the results dynamically on the mobile phone screen.

Abstract: A fetal parameter or anatomy is measured or detected from three-dimensional ultrasound data. An algorithm is machine-trained to detect fetal anatomy. Any machine training approach may be used. The machine-trained classifier is a joint classifier, such that one anatomy is detected using the ultrasound data and the detected location of another anatomy. The machine-trained classifier uses marginal space such that the location of anatomy is detected sequentially through translation, orientation and scale rather than detecting for all location parameters at once. The machine-trained classifier includes detectors for detecting from the ultrasound data at different resolutions, such as in a pyramid volume.

Abstract: A gas concentration estimation device of a coal-burning boiler adapted to estimate the concentration of the gas component included in an exhaust gas emitted from a coal-burning boiler using a neural network, including: a process database section adapted to store process data of a coal-burning boiler; a filtering processing section adapted to perform filtering processing for extracting data suitable for learning of a neural network from the process data stored in the process database section; a neural-network learning processing section adapted to perform learning processing of the neural network based on the data extracted by the filtering processing section and suitable for learning of the neural network; and a neural-network estimation processing section adapted to perform estimation processing of the CO concentration or the NOx concentration in the exhaust gas emitted from the coal-burning boiler based on the learning processing of the neural-network learning processing section.

Abstract: A method and system are provided for generating a nonlinear simulation model of a device under test (DUT). The method and system include receiving large-signal nonlinear waveform data based on responses of the DUT to input signals, determining a set of first dynamical variables and a set of second dynamical variables from the nonlinear waveform data, calculating values of second dynamical variables, providing nonlinear constitutive relations as functions of the first dynamical variables and the calculated values of the second dynamical variables, and compiling the nonlinear simulation model of the DUT using the identified nonlinear constitutive relations.

Abstract: A mobile station is arranged to determine its location, which is searched against street addresses from a database, and at least one matching street address is retrieved. The street address is searched on the mobile station and/or over the network. The search engine conducts a search in the mobile station file system and/or the Internet and/or a file system over the network with the at least one query term, —at least one search result is arranged to be displayed to user on the screen of the mobile station. This facilitates on-demand effortless Mobile Internet Search that allows the users to access opportunities that they did not know about, or would not have had time to find out about with minimum effort as the software of the mobile phone is scanning the Internet and information pages for these opportunities and displaying the results dynamically on the mobile phone screen.

Abstract: An apparatus, system, and method are disclosed for identifying a target object. An object detection module detects objects by matching data from one or more sensors to known data of a target object and determining one or more correlation metrics for each object. An object tracking module tracks geographic locations for detected objects over time using subsequent data from the one or more sensors. A contextual data module determines one or more contextual indicators for detected objects based on the data from the one or more sensors. An artificial intelligence module estimates probabilities that detected objects comprise the target object based on the correlation metrics, the geographic locations, the contextual indicators, and one or more target contextual indicators associated with the target object. The artificial intelligence module estimates the probabilities using an artificial intelligence model, such as a Bayesian network.

Abstract: Method and apparatus for template-based processing of electronic documents is described. In some examples, text content of the electronic documents is analyzed to identify whether each of the electronic documents matches any of a plurality of document templates. A template index is generated that relates at least one of the electronic documents with at least one of the plurality of document templates associated therewith. A search query is generated using at least one of the plurality of document templates as a respective at least one search parameter. An archive having the electronic documents is searched using the template index to locate any of the electronic documents that match the at least one document template of the search query.

Abstract: This invention is in the field of machine learning and neural associative memory. In particular the invention discloses a neural associative memory structure for storing and maintaining associations between memory address patterns and memory content patterns using a neural network, as well as methods for storing and retrieving such associations. Bayesian learning is applied to achieve non-linear learning.

Abstract: Embodiments of the invention provide neuromorphic-synaptronic systems, including neuromorphic-synaptronic circuits implementing spiking neural network with synaptic weights learned using simulation. One embodiment includes simulating a spiking neural network to generate synaptic weights learned via the simulation while maintaining one-to-one correspondence between the simulation and a digital circuit chip. The learned synaptic weights are loaded into the digital circuit chip implementing a spiking neural network, the digital circuit chip comprising a neuromorphic-synaptronic spiking neural network including plural synapse devices interconnecting multiple digital neurons.

Abstract: method for the open-loop control and/or closed-loop control of a filter system for the ultrafiltration of fluids, particularly for the ultrafiltration of water, with a filter, wherein the open-loop control and/or closed-loop control takes place on the basis of a fuzzy logic and/or artificial neural networks.

Abstract: A method of examining a cellular structure includes the steps of providing an inspecting device, a neural network and a target cellular structure that includes a plurality of target cells extending therethrough and further includes a target face exposing an arrangement of the target cells; inspecting the arrangement of cells on the face of the target cellular structure using the inspecting device; representing the arrangement of cells with numerically defined target cell parameters; inputting the target cell parameters into the neural network; and generating an output from the neural network based on the target cell parameters, the output being indicative of a strength of the target cellular structure.

Abstract: Certain aspects of the present disclosure provide methods and apparatus for spiking neural computation of general linear systems. One example aspect is a neuron model that codes information in the relative timing between spikes. However, synaptic weights are unnecessary. In other words, a connection may either exist (significant synapse) or not (insignificant or non-existent synapse). Certain aspects of the present disclosure use binary-valued inputs and outputs and do not require post-synaptic filtering. However, certain aspects may involve modeling of connection delays (e.g., dendritic delays). A single neuron model may be used to compute any general linear transformation x=AX+BU to any arbitrary precision. This neuron model may also be capable of learning, such as learning input delays (e.g., corresponding to scaling values) to achieve a target output delay (or output value). Learning may also be used to determine a logical relation of causal inputs.

Abstract: A method for the computer-aided learning of a recurrent neural network for modeling a dynamic system which is characterized at respective times by an observable vector with one or more observables as entries is provided. The neural network includes both a causal network with a flow of information that is directed forwards in time and a retro-causal network with a flow of information which is directed backwards in time. The states of the dynamic system are characterized by first state vectors in the causal network and by second state vectors in the retro-causal network, wherein the state vectors each contain observables for the dynamic system and also hidden states of the dynamic system. Both networks are linked to one another by a combination of the observables from the relevant first and second state vectors and are learned on the basis of training date including known observables vectors.

Abstract: Systems, methods, and apparatus are provided using signals from a set of tactile sensors mounted on a surface to determine the three-dimensional morphology (e.g., size, shape, orientation, and/or position) and texture of objects of arbitrary shape. Analytical, numerical, and/or neural network approaches can be used to interpret the sensory data.

Abstract: A method and system for adaptive auto-encoders is disclosed. An input audio training signal may be transformed into a sequence of feature vectors, each bearing quantitative measures of acoustic properties of the input audio training signal. An auto-encoder may process the feature vectors to generate an encoded form of the quantitative measures, and a recovered form of the quantitative measures based on an inverse operation by the auto-encoder on the encoded form of the quantitative measures. A duplicate copy of the sequence of feature vectors may be normalized to form a normalized signal in which supra-phonetic acoustic properties are reduced in comparison with phonetic acoustic properties of the input audio training signal. The auto-encoder may then be trained to compensate for supra-phonetic features by reducing the magnitude of an error signal corresponding to a difference between the normalized signal and the recovered form of the quantitative measures.

Abstract: Systems, methods, and apparatus are provided using signals from a set of tactile sensors mounted on a surface to determine a surface topography. An example method includes receiving a set of moment and force input data from one or more identified topographies. The example method includes using a neural network to receive input from a training data set based on the first set of moment and force input data from the one or more identified topographies. Network weights to be used by the neural network to produce the training data set are modified via an evolutionary algorithm that tests vectors of candidate network weights. The example method includes receiving a moment and force input from a test object surface and reconstructing the surface topology based on the neural network outputs.

Abstract: In one embodiment, the present invention provides a neural network comprising multiple modalities. Each modality comprises multiple neurons. The neural network further comprises an interconnection lattice for cross-associating signaling between the neurons in different modalities. The interconnection lattice includes a plurality of perception neuron populations along a number of bottom-up signaling pathways, and a plurality of action neuron populations along a number of top-down signaling pathways. Each perception neuron along a bottom-up signaling pathway has a corresponding action neuron along a reciprocal top-down signaling pathway. An input neuron population configured to receive sensory input drives perception neurons along a number of bottom-up signaling pathways. A first set of perception neurons along bottom-up signaling pathways drive a first set of action neurons along top-down signaling pathways.

Abstract: Methods, systems, and computer program products for determining availability of presentable content via a subscription service are disclosed. According to one aspect, a method includes receiving an indication of first presentable content associated with a first subscription service. Metadata associated with the selected first presentable content is received. Based on the received metadata, it is determined whether second presentable content corresponding to the first presentable content is available from a second subscription service. Further, and indication is provided that the second presentable content is available.

Abstract: Certain aspects of the present disclosure support a technique for neural learning of natural multi-spike trains in spiking neural networks. A synaptic weight can be adapted depending on a resource associated with the synapse, which can be depleted by weight change and can recover over time. In one aspect of the present disclosure, the weight adaptation may depend on a time since the last significant weight change.

Abstract: In a method for acquiring process parameters for a film, a computer divides parameter sets into a training data group and a test data group. Then, the computer inputs the training data group to a neural network (NN) so as to obtain relationship among parameter sets of the training data group and transmittances, and uses the test data group to estimate accuracy of the NN. Further, the computer modifies the NN until an error value of estimated parameters, which are acquired by the NN according to the obtained relationship, is smaller than a predetermined value, and uses the NN to acquire practical parameters corresponding to a target transmittance when the error value is smaller than the predetermined value.

Abstract: There is provided a method of generating a pulmonary index value of a patient, which includes receiving two or more measured patient parameters, wherein at least one of the measured parameters originates from a pulmonary sensor; and computing the pulmonary index value based on the two or more measured patient parameters.

Abstract: A computer-implemented method and system are provided for populating the content repository of the media service based on real-time media recommendation network comprising a plurality of peer devices. Aspects of the method and system include receiving by a server a recommendation from one of the plurality of peer devices for a media item that is intended for a recipient; determining if the media item is present in the content repository; in response to determining that the media item is not present in the content repository, requesting that the peer device upload the media item; and in response to the media item being uploaded, storing the media item in the content repository.

Abstract: Systems and methods for predicting energy usage of an asset are provided. Among several implementations of methods implemented by a computer, one embodiment of a computer-implemented method includes selecting one of a plurality of base temperatures that allows a linear equation to estimate energy consumption by an asset as a function of an average daily demand on the asset to attain a desired temperature. The computer-implemented method also includes inserting the selected base temperature in a non-linear equation for modeling the asset's energy consumption.

Abstract: A mental-model elicitation process and apparatus, called the Mental-Model Elicitation Device (MMED) is described. The MMED is used to give rise to more effective end-user mental-modeling activities that require executive function and working memory functionality. The method and apparatus is visual analysis based, allowing visual and other sensory representations to be given to thoughts, attitudes, and interpretations of a user about a given visualization of a mental-model, or aggregations of such visualizations and their respective blending. Other configurations of the apparatus and steps of the process may be created without departing from the spirit of the invention as disclosed.

Abstract: A method is for setting configuration data to a print data supplying device. The print data supplying device is operable to: store data associated with at least one of a plurality of items of group information in a first storage area; generate print data based on: (1) internal print data generated by an internal print data generation program; and (2) configuration data associated with one of the items of group information corresponding to a printer to which the print data is supplied; and supply the print data to the printer. The method includes: determining whether or not a target printer is connected; generating a new item of group information corresponding to the target printer when the target printer is connected; and storing reference configuration data that is stored in a second storage area to the first storage area, as the configuration data, in association with the new item of the group information.

Abstract: Systems and methods for arithmetic modeling of large scale engineer-to-order production systems using asynchronous stochastic learning curve are disclosed. In one embodiment, a method for simulating a production system configured to produce a product includes, for a plurality of components, assigning learning curve parameters for an asynchronous stochastic learning curve associated with each component. Master schedule data for manufacturing a plurality of the product are received, and production of the plurality of components a plurality of cycles corresponding to the plurality of the product is simulated. The results of the simulated productions are output for analysis. In a further aspect, the product is an aircraft, and the components are aircraft components.